Large Vision-Language Models (LVLMs) undergo safety alignment to suppress harmful content. However, current defenses predominantly target explicit malicious patterns in the input representation, often overlooking the vulnerabilities inherent in compositional reasoning. In this paper, we identify a systemic flaw where LVLMs can be induced to synthesize harmful logic from benign premises. We formalize this attack paradigm as \textit{Reasoning-Oriented Programming}, drawing a structural analogy to Return-Oriented Programming in systems security. Just as ROP circumvents memory protections by chaining benign instruction sequences, our approach exploits the model's instruction-following capability to orchestrate a semantic collision of orthogonal benign inputs. We instantiate this paradigm via \tool{}, an automated framework that optimizes for \textit{semantic orthogonality} and \textit{spatial isolation}. By generating visual gadgets that are semantically decoupled from the harmful intent and arranging them to prevent premature feature fusion, \tool{} forces the malicious logic to emerge only during the late-stage reasoning process. This effectively bypasses perception-level alignment. We evaluate \tool{} on SafeBench and MM-SafetyBench across 7 state-of-the-art 0.LVLMs, including GPT-4o and Claude 3.7 Sonnet. Our results demonstrate that \tool{} consistently circumvents safety alignment, outperforming the strongest existing baseline by an average of 4.67\% on open-source models and 9.50\% on commercial models.

Recent text-to-video (T2V) models can synthesize complex videos from lightweight natural language prompts, raising urgent concerns about safety alignment in the event of misuse in the real world. Prior jailbreak attacks typically rewrite unsafe prompts into paraphrases that evade content filters while preserving meaning. Yet, these approaches often still retain explicit sensitive cues in the input text and therefore overlook a more profound, video-specific weakness. In this paper, we identify a temporal trajectory infilling vulnerability of T2V systems under fragmented prompts: when the prompt specifies only sparse boundary conditions (e.g., start and end frames) and leaves the intermediate evolution underspecified, the model may autonomously reconstruct a plausible trajectory that includes harmful intermediate frames, despite the prompt appearing benign to input or output side filtering. Building on this observation, we propose TFM. This fragmented prompting framework converts an originally unsafe request into a temporally sparse two-frame extraction and further reduces overtly sensitive cues via implicit substitution. Extensive evaluations across multiple open-source and commercial T2V models demonstrate that TFM consistently enhances jailbreak effectiveness, achieving up to a 12% increase in attack success rate on commercial systems. Our findings highlight the need for temporally aware safety mechanisms that account for model-driven completion beyond prompt surface form.

Machine learning systems can produce personalized outputs that allow an adversary to infer sensitive input attributes at inference time. We introduce Robust Privacy (RP), an inference-time privacy notion inspired by certified robustness: if a model's prediction is provably invariant within a radius-$R$ neighborhood around an input $x$ (e.g., under the $\ell_2$ norm), then $x$ enjoys $R$-Robust Privacy, i.e., observing the prediction cannot distinguish $x$ from any input within distance $R$ of $x$. We further develop Attribute Privacy Enhancement (APE) to translate input-level invariance into an attribute-level privacy effect. In a controlled recommendation task where the decision depends primarily on a sensitive attribute, we show that RP expands the set of sensitive-attribute values compatible with a positive recommendation, expanding the inference interval accordingly. Finally, we empirically demonstrate that RP also mitigates model inversion attacks (MIAs) by masking fine-grained input-output dependence. Even at small noise levels ($σ=0.1$), RP reduces the attack success rate (ASR) from 73% to 4% with partial model performance degradation. RP can also partially mitigate MIAs (e.g., ASR drops to 44%) with no model performance degradation.

Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video (T2V) models typically add adversarial perturbations to obviously unsafe prompts, which are often easy to detect and defend. In contrast, we show that benign-looking prompts containing rich, implicit cues can induce T2V models to generate semantically unsafe videos that both violate policy and preserve the original (blocked) intent. To realize this, we propose VEIL, a jailbreak framework that leverages T2V models' cross-modal associative patterns via a modular prompt design. Specifically, our prompts combine three components: neutral scene anchors, which provide the surface-level scene description extracted from the blocked intent to maintain plausibility; latent auditory triggers, textual descriptions of innocuous-sounding audio events (e.g., creaking, muffled noises) that exploit learned audio-visual co-occurrence priors to bias the model toward particular unsafe visual concepts; and stylistic modulators, cinematic directives (e.g., camera framing, atmosphere) that amplify and stabilize the latent trigger's effect. We formalize attack generation as a constrained optimization over the above modular prompt space and solve it with a guided search procedure that balances stealth and effectiveness. Extensive experiments over 7 T2V models demonstrate the efficacy of our attack, achieving a 23 percent improvement in average attack success rate in commercial models. Our demos and codes can be found at https://github.com/NY1024/VEIL.

Multimodal large language models (MLLMs) exhibit remarkable capabilities but remain susceptible to jailbreak attacks exploiting cross-modal vulnerabilities. In this work, we introduce a novel method that leverages sequential comic-style visual narratives to circumvent safety alignments in state-of-the-art MLLMs. Our method decomposes malicious queries into visually innocuous storytelling elements using an auxiliary LLM, generates corresponding image sequences through diffusion models, and exploits the models' reliance on narrative coherence to elicit harmful outputs. Extensive experiments on harmful textual queries from established safety benchmarks show that our approach achieves an average attack success rate of 83.5\%, surpassing prior state-of-the-art by 46\%. Compared with existing visual jailbreak methods, our sequential narrative strategy demonstrates superior effectiveness across diverse categories of harmful content. We further analyze attack patterns, uncover key vulnerability factors in multimodal safety mechanisms, and evaluate the limitations of current defense strategies against narrative-driven attacks, revealing significant gaps in existing protections.

Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security evaluation benchmarks. Existing benchmarks provide only partial coverage, typically restricted to narrow scenarios such as user-level prompt manipulation, and thus fail to capture the broad range of agent vulnerabilities. To address this gap, we present \tool{}, the first holistic benchmark for evaluating the security of LVLM-based web agents. \tool{} first introduces a unified evaluation suite comprising six simulated but realistic web environments (\eg, e-commerce platforms, community forums) and includes 2,970 high-quality trajectories spanning diverse tasks and attack settings. The suite defines a structured taxonomy of six attack vectors spanning both user-level and environment-level manipulations. In addition, we introduce a multi-layered evaluation protocol that analyzes agent failures across three critical dimensions: internal reasoning, behavioral trajectory, and task outcome, facilitating a fine-grained risk analysis that goes far beyond simple success metrics. Using this benchmark, we conduct large-scale experiments on 9 representative LVLMs, which fall into three categories: general-purpose, agent-specialized, and GUI-grounded. Our results show that all tested agents are consistently vulnerable to subtle adversarial manipulations and reveal critical trade-offs between model specialization and security. By providing (1) a comprehensive benchmark suite with diverse environments and a multi-layered evaluation pipeline, and (2) empirical insights into the security challenges of modern LVLM-based web agents, \tool{} establishes a foundation for advancing trustworthy web agent deployment.

Jailbreak attacks on Large Language Models (LLMs) have demonstrated various successful methods whereby attackers manipulate models into generating harmful responses that they are designed to avoid. Among these, Greedy Coordinate Gradient (GCG) has emerged as a general and effective approach that optimizes the tokens in a suffix to generate jailbreakable prompts. While several improved variants of GCG have been proposed, they all rely on fixed-length suffixes. However, the potential redundancy within these suffixes remains unexplored. In this work, we propose Mask-GCG, a plug-and-play method that employs learnable token masking to identify impactful tokens within the suffix. Our approach increases the update probability for tokens at high-impact positions while pruning those at low-impact positions. This pruning not only reduces redundancy but also decreases the size of the gradient space, thereby lowering computational overhead and shortening the time required to achieve successful attacks compared to GCG. We evaluate Mask-GCG by applying it to the original GCG and several improved variants. Experimental results show that most tokens in the suffix contribute significantly to attack success, and pruning a minority of low-impact tokens does not affect the loss values or compromise the attack success rate (ASR), thereby revealing token redundancy in LLM prompts. Our findings provide insights for developing efficient and interpretable LLMs from the perspective of jailbreak attacks.