Safety Vulnerabilities

A semantic slot filling vulnerability in Large Vision-Language Models (LVLMs) allows attackers to bypass safety filters and elicit prohibited content via a single query. The attack, known as StructAttack, decomposes a harmful instruction into a central topic and locally benign-appearing semantic slot types (e.g., "Raw Materials", "Making Process"). These individual slots are embedded into structured visual prompts (such as mind maps, tables, or sunburst diagrams) alongside harmless distractor…

The OpenClaw autonomous agent framework lacks execution sandboxing, running agents directly on the host machine with the disk and system privileges of the host user. This architecture allows attackers to achieve Remote Code Execution (RCE) and arbitrary data exfiltration via Indirect Prompt Injection. By embedding malicious instructions within external data sources (e.g., scraped web pages or uploaded documents), an attacker can hijack the agent's planning capabilities to sequentially chain…

GPT-OSS-Safeguard-20B and Meta-SecAlign (70B/8B) are vulnerable to white-box adversarial attacks generated by automated algorithmic recombination (specifically the claude_v63, claude_v82, and claude_v53-oss optimizers). These algorithms significantly outperform standard discrete optimization methods (like GCG) by integrating continuous optimization (ADC) with LayerNorm gradient scaling (LSGM), or by merging momentum-smoothed gradients with directional perturbation candidate selection (DPTO)…

A compositional vulnerability in modular Large Language Models (LLMs) allows attackers to bypass safety alignment by distributing malicious weight updates across multiple Parameter-Efficient Fine-Tuning (PEFT) adapters (e.g., LoRA). The malicious adapters are anchored to valid functional subspaces (e.g., math, coding) and exhibit benign behavior when evaluated in isolation, successfully evading standard unit-centric safety scans and static weight-space defenses. However, when a user linearly…

An "in-content harm" vulnerability exists in safety-aligned Large Language Models (LLMs) where task-level alignment mechanisms fail to evaluate the safety of user-provided external data. Attackers can bypass safety guardrails by embedding policy-violating text (e.g., violence, self-harm, explicit content) within the payload of a seemingly benign, policy-compliant task (e.g., translation, summarization, grammar polishing). Because the primary instruction is harmless, the LLM's safety filters…

Large Language Models (LLMs) are vulnerable to a jailbreak technique termed "Priority Hacking." Adversaries can bypass safety alignments by exploiting the model's internal priority graph, where certain abstract values (e.g., justice, public health) implicitly outweigh general safety restrictions within specific contexts. By crafting a deceptive prompt that frames a malicious request as a necessary action in service of a higher-priority benign value, attackers engineer a value conflict. The…

Leading Large Language Models (LLMs) exhibit significant cross-lingual safety drift, allowing users to bypass safety guardrails by translating harmful prompts into low-resource Indic languages. While models effectively block unsafe prompts concerning caste, religion, gender, and politics in high-resource languages like English and Hindi, their safety alignment severely degrades in low-resource scripts such as Odia, Telugu, Kannada, and Punjabi. Evaluated models demonstrate a cross-language…

An activation-steering vulnerability in open-weights Large Language Models allows attackers to bypass safety guardrails by injecting targeted additive perturbations into deep, safety-critical attention heads. The exploit, termed Safety Attention Head Attack (SAHA), utilizes Ablation-Impact Ranking (AIR) to isolate specific attention heads that causally govern safety refusals. By applying Layer-Wise Perturbations (LWP) derived from the linearized decision boundary of a latent safety probe, an…

A prompt structure vulnerability exists in instruction-tuned Large Language Models (LLMs) where attackers can bypass safety alignments by injecting a continuation-triggering suffix immediately following the user prompt termination token. By placing an affirmative suffix outside the user instruction boundary, it is processed as the beginning of the assistant's own pre-filled response. This structural manipulation intrinsically overactivates the model's continuation attention heads, forcing its…

Embodied Large Language Models (LLMs) used for real-world agent planning are vulnerable to Action-level Manipulation (dubbed "Blindfold"), a jailbreak technique that bypasses semantic-level safety filters by exploiting the models' limited spatial and causal reasoning regarding physical consequences. Attackers can use an adversarial proxy LLM to decompose a semantically harmful intent into a sequence of individually benign primitive actions. To evade advanced semantic correlation checks…