Safety Vulnerabilities

A vulnerability exists in Large Vision-Language Models (LVLMs) utilizing visual token compression mechanisms (e.g., VisionZip, VisPruner) to reduce inference latency. The vulnerability stems from an optimization-inference mismatch where standard adversarial defenses assume full-token processing, while the deployed model utilizes a subset of tokens selected via importance metrics (typically attention scores).

Large Vision-Language Models (LVLMs) are vulnerable to Physical Prompt Injection Attacks (PPIA), a query-agnostic injection technique delivered via the visual modality. The vulnerability stems from the model's "Vision-Enabled Text Recognition" capabilities and "Identity Sensitivity," where the model interprets text embedded in the physical environment (e.g., printed on signs, posters, or objects) as high-priority instructions rather than passive visual data. An attacker can embed adversarial…

Open-weight Large Language Models (LLMs) are vulnerable to a white-box safety alignment bypass known as "abliteration" (directional orthogonalization). An attacker with access to the model weights can compute the "refusal direction" in the residual stream activation space by contrasting internal activations between harmful and harmless prompts. By projecting the model's weight matrices to be orthogonal to this single direction (or specific concept cones), the safety alignment is surgically…

LLM-based code agents and vulnerability detectors employing Chain-of-Thought (CoT) reasoning are susceptible to automated adversarial code obfuscation. The vulnerability exists because CoT mechanisms expose the model's decision logic, allowing reinforcement learning frameworks (such as CoTDeceptor) to iteratively refine code transformations based on the detector's own reasoning traces. By optimizing for "reasoning instability" and "hallucination" rather than just syntactic evasion, attackers…

Large Language Model (LLM) agents operating in tool-augmented environments are susceptible to "Contextual Fragility" and multi-turn "long-chain" exploitation. Existing safety mechanisms predominantly function on a stateless, atomic paradigm, evaluating individual input-output pairs in isolation. This allows an adversary to orchestrate complex attack trajectories where malicious intent is distributed across multiple, individually benign steps (a "Domino Effect"). Consequently, an attacker can…

Commercial Multimodal Large Language Model (MLLM) integrated systems are vulnerable to a "Dual Steganography" jailbreak paradigm (referred to as Odysseus). The vulnerability arises from the reliance of safety filters on the assumption that malicious content must be explicitly visible in the input or output modalities (text or image). Attackers can bypass these filters by encoding malicious queries into binary matrices and embedding them into benign-looking images using steganographic encoders…

Frontier Large Language Models (LLMs) exhibit a critical vulnerability to automated, adaptive multi-turn adversarial attacks, specifically those utilizing tree-based exploration algorithms (e.g., the TEMPEST framework). Unlike single-turn jailbreaks, this vulnerability exploits the model's inability to maintain safety alignment across extended conversation trajectories. An attacker using an automated agent can dynamically select from multiple adversarial strategies—such as academic framing…

A vulnerability exists in OpenAI's Custom GPTs platform where the lack of effective isolation between the system context ("Expert Prompt"), external knowledge retrieval, and user input allows for unauthorized information disclosure and tool misuse. By employing specific prompt injection techniques—including Hex injection, Many-shot prefix attacks, and Knowledge Poisoning (uploading malicious files)—an attacker can bypass safety guardrails. This results in the extraction of proprietary system…

A vulnerability exists in MetaGPT's DataInterpreter agent (and similar RAG-based agents utilizing persistent long-term memory) that allows for persistent memory poisoning via indirect injection. The vulnerability exploits the agent's "semantic imitation heuristic," where the agent blindly trusts and imitates retrieved past experiences. An attacker can supply a benign-looking artifact (e.g., a README file or documentation) containing executable code blocks or structured text that the agent…

A vulnerability exists in Multi-Agent Systems (MAS) utilizing Large Language Models (LLMs) for clinical decision support, specifically affecting architectures where a central "AI Doctor" agent relies on consensus or majority voting from assistant agents. The vulnerability, termed "Many-to-One Adversarial Consensus," allows a coalition of colluding adversarial agents to override the central agent's safety alignment and internal knowledge. By fabricating a false consensus (typically requiring $k…