Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection (IPI), a black-box attack in which adversarial instructions are embedded into natural images to override model behavior. Our end-to-end IPI pipeline incorporates segmentation-based region selection, adaptive font scaling, and background-aware rendering to conceal prompts from human perception while preserving model interpretability. Using the COCO dataset and GPT-4-turbo, we evaluate 12 adversarial prompt strategies and multiple embedding configurations. The results show that IPI can reliably manipulate the output of the model, with the most effective configuration achieving up to 64\% attack success under stealth constraints. These findings highlight IPI as a practical threat in black-box settings and underscore the need for defenses against multimodal prompt injection.

The rapid development of large language models (LLMs) has driven the widespread adoption of cloud-based LLM inference services, while also bringing prominent privacy risks associated with the transmission and processing of private data in remote inference. For privacy-preserving LLM inference technologies to be practically applied in industrial scenarios, three core requirements must be satisfied simultaneously: (1) Accuracy and efficiency losses should be minimized to mitigate degradation in service experience. (2) The inference process can be run on large-scale clusters consist of heterogeneous legacy xPUs. (3) Compatibility with existing LLM infrastructures should be ensured to reuse their engineering optimizations. To the best of our knowledge, none of the existing privacy-preserving LLM inference methods satisfy all the above constraints while delivering meaningful privacy guarantees. In this paper, we propose AloePri, the first privacy-preserving LLM inference method for industrial applications. AloePri protects both the input and output data by covariant obfuscation, which jointly transforms data and model parameters to achieve better accuracy and privacy. We carefully design the transformation for each model component to ensure inference accuracy and data privacy while keeping full compatibility with existing infrastructures of Language Model as a Service. AloePri has been integrated into an industrial system for the evaluation of mainstream LLMs. The evaluation on Deepseek-V3.1-Terminus model (671B parameters) demonstrates that AloePri causes accuracy loss of 0.0%~3.5% and exhibits efficiency equivalent to that of plaintext inference. Meanwhile, AloePri successfully resists state-of-the-art attacks, with less than 5\% of tokens recovered. To the best of our knowledge, AloePri is the first method to exhibit practical applicability to large-scale models in real-world systems.

Multi-tenant LLM serving frameworks widely adopt shared Key-Value caches to enhance efficiency. However, this creates side-channel vulnerabilities enabling prompt leakage attacks. Prior studies identified these attack surfaces yet focused on expanding attack vectors rather than optimizing attack performance, reporting impractically high attack costs that underestimate the true privacy risk. We propose OptiLeak, a reinforcement learning-enhanced framework that maximizes prompt reconstruction efficiency through two-stage fine-tuning. Our key insight is that domain-specific ``hard tokens'' -- terms difficult to predict yet carrying sensitive information -- can be automatically identified via likelihood ranking and used to construct preference pairs for Direct Preference Optimization, eliminating manual annotation. This enables effective preference alignment while avoiding the overfitting issues of extended supervised fine-tuning. Evaluated on three benchmarks spanning medical and financial domains, OptiLeak achieves up to $12.48\times$ reduction in average requests per token compared to baseline approaches, with consistent improvements across model scales from 3B to 14B parameters. Our findings demonstrate that cache-based prompt leakage poses a more severe threat than previously reported, underscoring the need for robust cache isolation in production deployments.

Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly vulnerable to jailbreak attacks that bypass safety alignment and induce harmful behaviors. Existing benchmarks such as JailBreakV-28K, MM-SafetyBench, and HADES provide valuable insights into multi-modal vulnerabilities, but they typically focus on limited attack scenarios, lack standardized defense evaluation, and offer no unified, reproducible toolbox. To address these gaps, we introduce OmniSafeBench-MM, which is a comprehensive toolbox for multi-modal jailbreak attack-defense evaluation. OmniSafeBench-MM integrates 13 representative attack methods, 15 defense strategies, and a diverse dataset spanning 9 major risk domains and 50 fine-grained categories, structured across consultative, imperative, and declarative inquiry types to reflect realistic user intentions. Beyond data coverage, it establishes a three-dimensional evaluation protocol measuring (1) harmfulness, distinguished by a granular, multi-level scale ranging from low-impact individual harm to catastrophic societal threats, (2) intent alignment between responses and queries, and (3) response detail level, enabling nuanced safety-utility analysis. We conduct extensive experiments on 10 open-source and 8 closed-source MLLMs to reveal their vulnerability to multi-modal jailbreak. By unifying data, methodology, and evaluation into an open-source, reproducible platform, OmniSafeBench-MM provides a standardized foundation for future research. The code is released at https://github.com/jiaxiaojunQAQ/OmniSafeBench-MM.

Sequential Recommenders, which exploit dynamic user intents through interaction sequences, is vulnerable to adversarial attacks. While existing attacks primarily rely on data poisoning, they require large-scale user access or fake profiles thus lacking practicality. In this paper, we focus on the Profile Pollution Attack that subtly contaminates partial user interactions to induce targeted mispredictions. Previous PPA methods suffer from two limitations, i.e., i) over-reliance on sequence horizon impact restricts fine-grained perturbations on item transitions, and ii) holistic modifications cause detectable distribution shifts. To address these challenges, we propose a constrained reinforcement driven attack CREAT that synergizes a bi-level optimization framework with multi-reward reinforcement learning to balance adversarial efficacy and stealthiness. We first develop a Pattern Balanced Rewarding Policy, which integrates pattern inversion rewards to invert critical patterns and distribution consistency rewards to minimize detectable shifts via unbalanced co-optimal transport. Then we employ a Constrained Group Relative Reinforcement Learning paradigm, enabling step-wise perturbations through dynamic barrier constraints and group-shared experience replay, achieving targeted pollution with minimal detectability. Extensive experiments demonstrate the effectiveness of CREAT.

Large Vision-Language Models (VLMs) are susceptible to jailbreak attacks: researchers have developed a variety of attack strategies that can successfully bypass the safety mechanisms of VLMs. Among these approaches, jailbreak methods based on the Out-of-Distribution (OOD) strategy have garnered widespread attention due to their simplicity and effectiveness. This paper further advances the in-depth understanding of OOD-based VLM jailbreak methods. Experimental results demonstrate that jailbreak samples generated via mild OOD strategies exhibit superior performance in circumventing the safety constraints of VLMs--a phenomenon we define as ''weak-OOD''. To unravel the underlying causes of this phenomenon, this study takes SI-Attack, a typical OOD-based jailbreak method, as the research object. We attribute this phenomenon to a trade-off between two dominant factors: input intent perception and model refusal triggering. The inconsistency in how these two factors respond to OOD manipulations gives rise to this phenomenon. Furthermore, we provide a theoretical argument for the inevitability of such inconsistency from the perspective of discrepancies between model pre-training and alignment processes. Building on the above insights, we draw inspiration from optical character recognition (OCR) capability enhancement--a core task in the pre-training phase of mainstream VLMs. Leveraging this capability, we design a simple yet highly effective VLM jailbreak method, whose performance outperforms that of SOTA baselines.

The widespread application of large VLMs makes ensuring their secure deployment critical. While recent studies have demonstrated jailbreak attacks on VLMs, existing approaches are limited: they require either white-box access, restricting practicality, or rely on manually crafted patterns, leading to poor sample diversity and scalability. To address these gaps, we propose JPRO, a novel multi-agent collaborative framework designed for automated VLM jailbreaking. It effectively overcomes the shortcomings of prior methods in attack diversity and scalability. Through the coordinated action of four specialized agents and its two core modules: Tactic-Driven Seed Generation and Adaptive Optimization Loop, JPRO generates effective and diverse attack samples. Experimental results show that JPRO achieves over a 60\% attack success rate on multiple advanced VLMs, including GPT-4o, significantly outperforming existing methods. As a black-box attack approach, JPRO not only uncovers critical security vulnerabilities in multimodal models but also offers valuable insights for evaluating and enhancing VLM robustness.

Vision-Language Models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalizability across diverse downstream tasks. However, recent studies have revealed that VLMs, including CLIP, are highly vulnerable to adversarial attacks, particularly on their visual modality. Traditional methods for improving adversarial robustness, such as adversarial training, involve extensive retraining and can be computationally expensive. In this paper, we propose a new Test-Time defense: Feature Perception Threshold Counterattack Noise (FPT-Noise), which enhances the adversarial robustness of CLIP without costly fine-tuning. Our core contributions are threefold: First, we introduce a Dynamic Feature Modulator that dynamically generate an image-specific and attack-adaptive noise intensity parameter. Second, We reanalyzed the image features of CLIP. When images are exposed to different levels of noise, clean images and adversarial images exhibit distinct rates of feature change. We established a feature perception threshold to distinguish clean images from attacked ones. Finally, we integrate a Scene-Aware Regulation guided by a stability threshold and leverage Test-Time Transformation Ensembling (TTE) to further mitigate the impact of residual noise and enhance robustness.Extensive experimentation has demonstrated that FPT-Noise significantly outperforms existing Test-Time defense methods, boosting average robust accuracy from 0.07% to 56.86% under AutoAttack while maintaining high performance on clean images (-1.1%). The code will be made public following the publication of the study. The code will be made public following the publication of the study.

Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this protection collapses once a harmful continuation is underway (either through the adversarial attacks or via harmful assistant-prefill attacks). This raises a fundamental question: Can the innate shallow alignment in LLMs be unlocked to ensure safety at arbitrary generation depths? To achieve this goal, we propose Any-Depth Alignment (ADA), an effective inference-time defense with negligible overhead. ADA is built based on our observation that alignment is concentrated in the assistant header tokens through repeated use in shallow-refusal training, and these tokens possess the model's strong alignment priors. By reintroducing these tokens mid-stream, ADA induces the model to reassess harmfulness and recover refusals at any point in generation. Across diverse open-source model families (Llama, Gemma, Mistral, Qwen, DeepSeek, and gpt-oss), ADA achieves robust safety performance without requiring any changes to the base model's parameters. It secures a near-100% refusal rate against challenging adversarial prefill attacks ranging from dozens to thousands of tokens. Furthermore, ADA reduces the average success rate of prominent adversarial prompt attacks (such as GCG, AutoDAN, PAIR, and TAP) to below 3%. This is all accomplished while preserving utility on benign tasks with minimal over-refusal. ADA maintains this resilience even after the base model undergoes subsequent instruction tuning (benign or adversarial).

We present a novel approach for attacking black-box large language models (LLMs) by exploiting their ability to express confidence in natural language. Existing black-box attacks require either access to continuous model outputs like logits or confidence scores (which are rarely available in practice), or rely on proxy signals from other models. Instead, we demonstrate how to prompt LLMs to express their internal confidence in a way that is sufficiently calibrated to enable effective adversarial optimization. We apply our general method to three attack scenarios: adversarial examples for vision-LLMs, jailbreaks and prompt injections. Our attacks successfully generate malicious inputs against systems that only expose textual outputs, thereby dramatically expanding the attack surface for deployed LLMs. We further find that better and larger models exhibit superior calibration when expressing confidence, creating a concerning security paradox where model capability improvements directly enhance vulnerability. Our code is available at this [link](https://github.com/zj-jayzhang/black_box_llm_optimization).

Large language models (LLMs) have grown more powerful in language generation, producing fluent text and even imitating personal style. Yet, this ability also heightens the risk of identity impersonation. To the best of our knowledge, no prior work has examined personalized machine-generated text (MGT) detection. In this paper, we introduce \dataset, the first benchmark for evaluating detector robustness in personalized settings, built from literary and blog texts paired with their LLM-generated imitations. Our experimental results demonstrate large performance gaps across detectors in personalized settings: some state-of-the-art models suffer significant drops. We attribute this limitation to the \textit{feature-inversion trap}, where features that are discriminative in general domains become inverted and misleading when applied to personalized text. Based on this finding, we propose \method, a simple and reliable way to predict detector performance changes in personalized settings. \method identifies latent directions corresponding to inverted features and constructs probe datasets that differ primarily along these features to evaluate detector dependence. Our experiments show that \method can accurately predict both the direction and the magnitude of post-transfer changes, showing 85\% correlation with the actual performance gaps. We hope that this work will encourage further research on personalized text detection.

The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It defines security boundaries, authenticates prompts, applies security rules and custom policies, and controls agentic behavior, enabling a defense-in-depth strategy. The A2AS framework avoids latency overhead, external dependencies, architectural changes, model retraining, and operational complexity. The BASIC security model is introduced as the A2AS foundation: (B) Behavior certificates enable behavior enforcement, (A) Authenticated prompts enable context window integrity, (S) Security boundaries enable untrusted input isolation, (I) In-context defenses enable secure model reasoning, (C) Codified policies enable application-specific rules. This first paper in the series introduces the BASIC security model and the A2AS framework, exploring their potential toward establishing the A2AS industry standard.

Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classification proves insufficient when models encounter ethical dilemmas, where the capacity to reason through moral trade-offs creates a distinct attack surface. We formalize this vulnerability through TRIAL, a multi-turn red-teaming methodology that embeds harmful requests within ethical framings. TRIAL achieves high attack success rates across most tested models by systematically exploiting the model's ethical reasoning capabilities to frame harmful actions as morally necessary compromises. Building on these insights, we introduce ERR (Ethical Reasoning Robustness), a defense framework that distinguishes between instrumental responses that enable harmful outcomes and explanatory responses that analyze ethical frameworks without endorsing harmful acts. ERR employs a Layer-Stratified Harm-Gated LoRA architecture, achieving robust defense against reasoning-based attacks while preserving model utility.

Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces critical security risks, particularly in the presence of prompt injection attacks. In this work, we propose a novel insight that treats the agent runtime traces as structured programs with analyzable semantics. Thus, we present AgentArmor, a program analysis framework that converts agent traces into graph intermediate representation-based structured program dependency representations (e.g., CFG, DFG, and PDG) and enforces security policies via a type system. AgentArmor consists of three key components: (1) a graph constructor that reconstructs the agent's runtime traces as graph-based intermediate representations with control and data flow described within; (2) a property registry that attaches security-relevant metadata of interacted tools \& data, and (3) a type system that performs static inference and checking over the intermediate representation. By representing agent behavior as structured programs, AgentArmor enables program analysis for sensitive data flow, trust boundaries, and policy violations. We evaluate AgentArmor on the AgentDojo benchmark, the results show that AgentArmor can reduce the ASR to 3\%, with the utility drop only 1\%.