Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this recommendation-seeking behavior to inject unauthorized advertisements. Unlike traditional pattern-triggered backdoors that rely on artificial triggers such as pixel patches or special tokens, Hidden Ads activates on natural user behaviors: when users upload images containing semantic content of interest (e.g., food, cars, animals) and ask recommendation-seeking questions, the backdoored model provides correct, helpful answers while seamlessly appending attacker-specified promotional slogans. This design preserves model utility and produces natural-sounding injections, making the attack practical for real-world deployment in consumer-facing recommendation services. We propose a multi-tier threat framework to systematically evaluate Hidden Ads across three adversary capability levels: hard prompt injection, soft prompt optimization, and supervised fine-tuning. Our poisoned data generation pipeline uses teacher VLM-generated chain-of-thought reasoning to create natural trigger--slogan associations across multiple semantic domains. Experiments on three VLM architectures demonstrate that Hidden Ads achieves high injection efficacy with near-zero false positives while maintaining task accuracy. Ablation studies confirm that the attack is data-efficient, transfers effectively to unseen datasets, and scales to multiple concurrent domain-slogan pairs. We evaluate defenses including instruction-based filtering and clean fine-tuning, finding that both fail to remove the backdoor without causing significant utility degradation.

Federated learning (FL) has attracted substantial attention in both academia and industry, yet its practical security posture remains poorly understood. In particular, a large body of poisoning research is evaluated under idealized assumptions about attacker participation, client homogeneity, and success metrics, which can substantially distort how security risks are perceived in deployed FL systems. This paper revisits FL security from a measurement perspective. We systematize three major sources of mismatch between research and practice: unrealistic poisoning threat models, the omission of hybrid heterogeneity, and incomplete metrics that overemphasize peak attack success while ignoring stability and utility cost. To study these gaps, we build TFLlib, a uniform evaluation framework that supports image, text, and tabular FL tasks and re-implements representative poisoning attacks under practical settings. Our empirical study shows that idealized evaluation often overstates security risk. Under practical settings, attack performance becomes markedly more dataset-dependent and unstable, and several attacks that appear consistently strong in idealized FL lose effectiveness or incur clear benign-task degradation once practical constraints are enforced. These findings further show that final-round attack success alone is insufficient for security assessment; practical measurement must jointly consider effectiveness, temporal stability, and collateral utility loss. Overall, this work argues that many conclusions in the FL poisoning literature are not directly transferable to real deployments. By tightening the threat model and using measurement protocols aligned with practice, we provide a more realistic view of the security risks faced by contemporary FL systems and distill concrete guidance for future FL security evaluation. Our code is available at https://github.com/xaddwell/TFLlib

We study how to allocate a fixed supervised fine-tuning budget when three objectives must be balanced at once: multi-turn safety alignment, low over-refusal on benign boundary queries, and instruction following under verifiable constraints. We propose MOSAIC (Multi-Objective Slice-Aware Iterative Curation for Alignment), a multi-objective framework for closed-loop data mixture search built on a unified L1-L3 evaluation interface. MOSAIC turns slice-level failure profiles into executable data actions, including dataset-level mixture ratios, bucket-level weights, and focus criteria. Under a fixed 1M-token budget and five rounds of independent fine-tuning from the same base model, MOSAIC improves internal XGuard from 2.76 to 4.67 while keeping OrBench at 4.41 and IFEval at 3.65. The final Pareto solution also generalizes better than a random static LoRA baseline on independent attack, over-refusal, and capability tests, suggesting that structured failure diagnosis can serve as a practical control signal for budgeted data construction. Code is available at https://github.com/douyipu/mosaic.

Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be maliciously activated at test time. Existing defenses typically rely on retraining backdoored parameters (e.g., adapters or LoRA modules) with clean data, which is computationally expensive and often degrades model performance. In this work, we provide a new mechanistic understanding of backdoor behaviors in LVLMs: the trigger does not influence prediction through low-level visual patterns, but through abnormal cross-modal attention redistribution, where trigger-bearing visual tokens steal attention away from the textual context - a phenomenon we term attention stealing. Motivated by this, we propose CleanSight, a training-free, plug-and-play defense that operates purely at test time. CleanSight (i) detects poisoned inputs based on the relative visual-text attention ratio in selected cross-modal fusion layers, and (ii) purifies the input by selectively pruning the suspicious high-attention visual tokens to neutralize the backdoor activation. Extensive experiments show that CleanSight significantly outperforms existing pixel-based purification defenses across diverse datasets and backdoor attack types, while preserving the model's utility on both clean and poisoned samples.

With the rapid advancement of AIGC technologies, image forensics will encounter unprecedented challenges. Traditional methods are incapable of dealing with increasingly realistic images generated by rapidly evolving image generation techniques. To facilitate the identification of AI-generated images and the attribution of their source models, generative image watermarking and AI-generated image attribution have emerged as key research focuses in recent years. However, existing methods are model-dependent, requiring access to the generative models and lacking generality and scalability to new and unseen generators. To address these limitations, this work presents a new paradigm for AI-generated image attribution by formulating it as an instance retrieval problem instead of a conventional image classification problem. We propose an efficient model-agnostic framework, called Low-bIt-plane-based Deepfake Attribution (LIDA). The input to LIDA is produced by Low-Bit Fingerprint Generation module, while the training involves Unsupervised Pre-Training followed by subsequent Few-Shot Attribution Adaptation. Comprehensive experiments demonstrate that LIDA achieves state-of-the-art performance for both Deepfake detection and image attribution under zero- and few-shot settings. The code is at https://github.com/hongsong-wang/LIDA

As 3D Gaussian Splatting becomes the de facto representation for interactive 3D assets, robust yet imperceptible watermarking is critical. We present a representation-native framework that separates where to write from how to preserve quality. A Trio-Experts module operates directly on Gaussian primitives to derive priors for carrier selection, while a Safety and Budget Aware Gate (SBAG) allocates Gaussians to watermark carriers, optimized for bit resilience under perturbation and bitrate budgets, and to visual compensators that are insulated from watermark loss. To maintain fidelity, we introduce a channel-wise group mask that controls gradient propagation for carriers and compensators, thereby limiting Gaussian parameter updates, repairing local artifacts, and preserving high-frequency details without increasing runtime. Our design yields view-consistent watermark persistence and strong robustness against common image distortions such as compression and noise, while achieving a favorable robustness-quality trade-off compared with prior methods. In addition, decoupled finetuning provides per-Gaussian attributions that reveal where the message is carried and why those carriers are selected, enabling auditable explainability. Compared with state-of-the-art methods, our approach achieves a PSNR improvement of +0.83 dB and a bit-accuracy gain of +1.24%.

The rapid adoption of vision-language models (VLMs) has heightened the demand for robust intellectual property (IP) protection of these high-value pretrained models. Effective IP protection should proactively confine model deployment within authorized domains and prevent unauthorized transfers. However, existing methods rely on static training-time definitions, limiting flexibility in dynamic environments and often producing opaque responses to unauthorized inputs. To address these limitations, we propose a novel dynamic authorization with legality-aware intellectual property protection (AoD-IP) for VLMs, a framework that supports authorize-on-demand and legality-aware assessment. AoD-IP introduces a lightweight dynamic authorization module that enables flexible, user-controlled authorization, allowing users to actively specify or switch authorized domains on demand at deployment time. This enables the model to adapt seamlessly as application scenarios evolve and provides substantially greater extensibility than existing static-domain approaches. In addition, AoD-IP incorporates a dual-path inference mechanism that jointly predicts input legality-aware and task-specific outputs. Comprehensive experimental results on multiple cross-domain benchmarks demonstrate that AoD-IP maintains strong authorized-domain performance and reliable unauthorized detection, while supporting user-controlled authorization for adaptive deployment in dynamic environments.

Adversarial training has emerged as a highly effective way to improve the robustness of deep neural networks (DNNs). It is typically conceptualized as a min-max optimization problem over model weights and adversarial perturbations, where the weights are optimized using gradient descent methods, such as SGD. In this paper, we propose a novel approach by treating model weights as random variables, which paves the way for enhancing adversarial training through \textbf{S}econd-Order \textbf{S}tatistics \textbf{O}ptimization (S$^2$O) over model weights. We challenge and relax a prevalent, yet often unrealistic, assumption in prior PAC-Bayesian frameworks: the statistical independence of weights. From this relaxation, we derive an improved PAC-Bayesian robust generalization bound. Our theoretical developments suggest that optimizing the second-order statistics of weights can substantially tighten this bound. We complement this theoretical insight by conducting an extensive set of experiments that demonstrate that S$^2$O not only enhances the robustness and generalization of neural networks when used in isolation, but also seamlessly augments other state-of-the-art adversarial training techniques. The code is available at https://github.com/Alexkael/S2O.

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets or simulated environments, failing to capture the security risks arising from dynamic code execution, tool interactions, and multi-turn context. To bridge this gap, we introduce CIBER, an automated benchmark that combines dynamic attack generation, isolated secure sandboxing, and state-aware evaluation to systematically assess the vulnerability of code interpreter agents against four major types of adversarial attacks: Direct/Indirect Prompt Injection, Memory Poisoning, and Prompt-based Backdoor. We evaluate six foundation models across two representative code interpreter agents (OpenInterpreter and OpenCodeInterpreter), incorporating a controlled study of identical models. Our results reveal that Interpreter Architecture and Model Alignment Set the Security Baseline. Structural integration enables aligned specialized models to outperform generic SOTA models. Conversely, high intelligence paradoxically increases susceptibility to complex adversarial prompts due to stronger instruction adherence. Furthermore, we identify a "Natural Language Disguise" Phenomenon, where natural language functions as a significantly more effective input modality than explicit code snippets (+14.1% ASR), thereby bypassing syntax-based defenses. Finally, we expose an alarming Security Polarization, where agents exhibit robust defenses against explicit threats yet fail catastrophically against implicit semantic hazards, highlighting a fundamental blind spot in current pattern-matching protection approaches.

Large Reasoning Models (LRMs) employ reasoning to address complex tasks. Such explicit reasoning requires extended context lengths, resulting in substantially higher resource consumption. Prior work has shown that adversarially crafted inputs can trigger redundant reasoning processes, exposing LRMs to resource-exhaustion vulnerabilities. However, the reasoning process itself, especially its reflective component, has received limited attention, even though it can lead to over-reflection and consume excessive computing power. In this paper, we introduce Recursive Entropy to quantify the risk of resource consumption in reflection, thereby revealing the safety issues inherent in inference itself. Based on Recursive Entropy, we introduce RECUR, a resource exhaustion attack via Recursive Entropy guided Counterfactual Utilization and Reflection. It constructs counterfactual questions to verify the inherent flaws and risks of LRMs. Extensive experiments demonstrate that, under benign inference, recursive entropy exhibits a pronounced decreasing trend. RECUR disrupts this trend, increasing the output length by up to 11x and decreasing throughput by 90%. Our work provides a new perspective on robust reasoning.

Spiking neural networks (SNNs) compute with discrete spikes and exploit temporal structure, yet most adversarial attacks change intensities or event counts instead of timing. We study a timing-only adversary that retimes existing spikes while preserving spike counts and amplitudes in event-driven SNNs, thus remaining rate-preserving. We formalize a capacity-1 spike-retiming threat model with a unified trio of budgets: per-spike jitter $\mathcal{B}_{\infty}$, total delay $\mathcal{B}_{1}$, and tamper count $\mathcal{B}_{0}$. Feasible adversarial examples must satisfy timeline consistency and non-overlap, which makes the search space discrete and constrained. To optimize such retimings at scale, we use projected-in-the-loop (PIL) optimization: shift-probability logits yield a differentiable soft retiming for backpropagation, and a strict projection in the forward pass produces a feasible discrete schedule that satisfies capacity-1, non-overlap, and the chosen budget at every step. The objective maximizes task loss on the projected input and adds a capacity regularizer together with budget-aware penalties, which stabilizes gradients and aligns optimization with evaluation. Across event-driven benchmarks (CIFAR10-DVS, DVS-Gesture, N-MNIST) and diverse SNN architectures, we evaluate under binary and integer event grids and a range of retiming budgets, and also test models trained with timing-aware adversarial training designed to counter timing-only attacks. For example, on DVS-Gesture the attack attains high success (over $90\%$) while touching fewer than $2\%$ of spikes under $\mathcal{B}_{0}$. Taken together, our results show that spike retiming is a practical and stealthy attack surface that current defenses struggle to counter, providing a clear reference for temporal robustness in event-driven SNNs. Code is available at https://github.com/yuyi-sd/Spike-Retiming-Attacks.

Diffusion-based face swapping achieves state-of-the-art performance, yet it also exacerbates the potential harm of malicious face swapping to violate portraiture right or undermine personal reputation. This has spurred the development of proactive defense methods. However, existing approaches face a core trade-off: large perturbations distort facial structures, while small ones weaken protection effectiveness. To address these issues, we propose FaceDefense, an enhanced proactive defense framework against diffusion-based face swapping. Our method introduces a new diffusion loss to strengthen the defensive efficacy of adversarial examples, and employs a directional facial attribute editing to restore perturbation-induced distortions, thereby enhancing visual imperceptibility. A two-phase alternating optimization strategy is designed to generate final perturbed face images. Extensive experiments show that FaceDefense significantly outperforms existing methods in both imperceptibility and defense effectiveness, achieving a superior trade-off.

Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy. In particular, fine-tuned models are highly vulnerable, as they are often fine-tuned on small and private datasets. Membership inference attacks (MIAs) are used to assess privacy risks by determining whether a specific sample was part of a model's training data. Existing MIAs against diffusion models either assume obtaining the intermediate results or require auxiliary datasets for training the shadow model. In this work, we utilized a critical yet overlooked vulnerability: the widely used noise schedules fail to fully eliminate semantic information in the images, resulting in residual semantic signals even at the maximum noise step. We empirically demonstrate that the fine-tuned diffusion model captures hidden correlations between the residual semantics in initial noise and the original images. Building on this insight, we propose a simple yet effective membership inference attack, which injects semantic information into the initial noise and infers membership by analyzing the model's generation result. Extensive experiments demonstrate that the semantic initial noise can strongly reveal membership information, highlighting the vulnerability of diffusion models to MIAs.

Recent advancements in multi-model AI systems have leveraged LLM routers to reduce computational cost while maintaining response quality by assigning queries to the most appropriate model. However, as classifiers, LLM routers are vulnerable to novel adversarial attacks in the form of LLM rerouting, where adversaries prepend specially crafted triggers to user queries to manipulate routing decisions. Such attacks can lead to increased computational cost, degraded response quality, and even bypass safety guardrails, yet their security implications remain largely underexplored. In this work, we bridge this gap by systematizing LLM rerouting threats based on the adversary's objectives (i.e., cost escalation, quality hijacking, and safety bypass) and knowledge. Based on the threat taxonomy, we conduct a measurement study of real-world LLM routing systems against existing LLM rerouting attacks. The results reveal that existing routing systems are vulnerable to rerouting attacks, especially in the cost escalation scenario. We then characterize existing rerouting attacks using interpretability techniques, revealing that they exploit router decision boundaries through confounder gadgets that prepend queries to force misrouting. To mitigate these risks, we introduce RerouteGuard, a flexible and scalable guardrail framework for LLM rerouting. RerouteGuard filters adversarial rerouting prompts via dynamic embedding-based detection and adaptive thresholding. Extensive evaluations in three attack settings and four benchmarks demonstrate that RerouteGuard achieves over 99% detection accuracy against state-of-the-art rerouting attacks, while maintaining negligible impact on legitimate queries. The experimental results indicate that RerouteGuard offers a principled and practical solution for safeguarding multi-model AI systems against adversarial rerouting.

While Large Language Models (LLMs) are aligned to mitigate risks, their safety guardrails remain fragile against jailbreak attacks. This reveals limited understanding of components governing safety. Existing methods rely on local, greedy attribution that assumes independent component contributions. However, they overlook the cooperative interactions between different components in LLMs, such as attention heads, which jointly contribute to safety mechanisms. We propose \textbf{G}lobal \textbf{O}ptimization for \textbf{S}afety \textbf{V}ector Extraction (GOSV), a framework that identifies safety-critical attention heads through global optimization over all heads simultaneously. We employ two complementary activation repatching strategies: Harmful Patching and Zero Ablation. These strategies identify two spatially distinct sets of safety vectors with consistently low overlap, termed Malicious Injection Vectors and Safety Suppression Vectors, demonstrating that aligned LLMs maintain separate functional pathways for safety purposes. Through systematic analyses, we find that complete safety breakdown occurs when approximately 30\% of total heads are repatched across all models. Building on these insights, we develop a novel inference-time white-box jailbreak method that exploits the identified safety vectors through activation repatching. Our attack substantially outperforms existing white-box attacks across all test models, providing strong evidence for the effectiveness of the proposed GOSV framework on LLM safety interpretability.

Navigation agents powered by large language models (LLMs) convert natural language instructions into executable plans and actions. Compared to text-based applications, their security is far more critical: a successful prompt injection attack does not just alter outputs but can directly misguide physical navigation, leading to unsafe routes, mission failure, or real-world harm. Despite this high-stakes setting, the vulnerability of navigation agents to prompt injection remains largely unexplored. In this paper, we propose PINA, an adaptive prompt optimization framework tailored to navigation agents under black-box, long-context, and action-executable constraints. Experiments on indoor and outdoor navigation agents show that PINA achieves high attack success rates with an average ASR of 87.5%, surpasses all baselines, and remains robust under ablation and adaptive-attack conditions. This work provides the first systematic investigation of prompt injection attacks in navigation and highlights their urgent security implications for embodied LLM agents.

Introducing reasoning models into Retrieval-Augmented Generation (RAG) systems enhances task performance through step-by-step reasoning, logical consistency, and multi-step self-verification. However, recent studies have shown that reasoning models suffer from overthinking attacks, where models are tricked to generate unnecessarily high number of reasoning tokens. In this paper, we reveal that such overthinking risk can be inherited by RAG systems equipped with reasoning models, by proposing an end-to-end attack framework named Contradiction-Based Deliberation Extension (CODE). Specifically, CODE develops a multi-agent architecture to construct poisoning samples that are injected into the knowledge base. These samples 1) are highly correlated with the use query, such that can be retrieved as inputs to the reasoning model; and 2) contain contradiction between the logical and evidence layers that cause models to overthink, and are optimized to exhibit highly diverse styles. Moreover, the inference overhead of CODE is extremely difficult to detect, as no modification is needed on the user query, and the task accuracy remain unaffected. Extensive experiments on two datasets across five commercial reasoning models demonstrate that the proposed attack causes a 5.32x-24.72x increase in reasoning token consumption, without degrading task performance. Finally, we also discuss and evaluate potential countermeasures to mitigate overthinking risks.

As Large Language Models (LLMs) evolve from static chatbots into autonomous agents capable of tool execution, the landscape of AI safety is shifting from content moderation to action security. However, existing red-teaming frameworks remain bifurcated: they either focus on rigid, script-based text attacks or lack the architectural modularity to simulate complex, multi-turn agentic exploitations. In this paper, we introduce AJAR (Adaptive Jailbreak Architecture for Red-teaming), a proof-of-concept framework designed to bridge this gap through Protocol-driven Cognitive Orchestration. Built upon the robust runtime of Petri, AJAR leverages the Model Context Protocol (MCP) to decouple adversarial logic from the execution loop, encapsulating state-of-the-art algorithms like X-Teaming as standardized, plug-and-play services. We validate the architectural feasibility of AJAR through a controlled qualitative case study, demonstrating its ability to perform stateful backtracking within a tool-use environment. Furthermore, our preliminary exploration of the "Agentic Gap" reveals a complex safety dynamic: while tool usage introduces new injection vectors via code execution, the cognitive load of parameter formatting can inadvertently disrupt persona-based attacks. AJAR is open-sourced to facilitate the standardized, environment-aware evaluation of this emerging attack surface. The code and data are available at https://github.com/douyipu/ajar.

The increasing misuse of AI-generated texts (AIGT) has motivated the rapid development of AIGT detection methods. However, the reliability of these detectors remains fragile against adversarial evasions. Existing attack strategies often rely on white-box assumptions or demand prohibitively high computational and interaction costs, rendering them ineffective under practical black-box scenarios. In this paper, we propose Multi-stage Alignment for Style Humanization (MASH), a novel framework that evades black-box detectors based on style transfer. MASH sequentially employs style-injection supervised fine-tuning, direct preference optimization, and inference-time refinement to shape the distributions of AI-generated texts to resemble those of human-written texts. Experiments across 6 datasets and 5 detectors demonstrate the superior performance of MASH over 11 baseline evaders. Specifically, MASH achieves an average Attack Success Rate (ASR) of 92%, surpassing the strongest baselines by an average of 24%, while maintaining superior linguistic quality.

Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, the practical effectiveness of existing attacks is undermined by several critical limitations: they struggle to maintain a coherent progression over long interactions, often losing track of what has been accomplished and what remains to be done; they rely on rigid or pre-defined patterns, and fail to adapt to the LLM's dynamic and unpredictable conversational state. To address these shortcomings, we introduce Mastermind, a multi-turn jailbreak framework that adopts a dynamic and self-improving approach. Mastermind operates in a closed loop of planning, execution, and reflection, enabling it to autonomously build and refine its knowledge of model vulnerabilities through interaction. It employs a hierarchical planning architecture that decouples high-level attack objectives from low-level tactical execution, ensuring long-term focus and coherence. This planning is guided by a knowledge repository that autonomously discovers and refines effective attack patterns by reflecting on interactive experiences. Mastermind leverages this accumulated knowledge to dynamically recombine and adapt attack vectors, dramatically improving both effectiveness and resilience. We conduct comprehensive experiments against state-of-the-art models, including GPT-5 and Claude 3.7 Sonnet. The results demonstrate that Mastermind significantly outperforms existing baselines, achieving substantially higher attack success rates and harmfulness ratings. Moreover, our framework exhibits notable resilience against multiple advanced defense mechanisms.