Language Model Security Database

Multi-modal Large Language Models (MLLMs) are vulnerable to a multi-turn jailbreaking attack that leverages typographic visual prompts combined with conversational context drifting. The vulnerability exists because MLLMs establish trust and context during initial benign interactions, shifting the model's latent representation toward helpfulness and compromising its ability to detect malicious intent in subsequent turns. The attack vector utilizes an image where a harmful request is…

A vulnerability exists in Large Language Model (LLM) and Large Reasoning Model (LRM) serving interfaces that allow user-defined response prefixes, such as plain text-completion (v1/completions), Fill-in-the-Middle (FIM), or assistant message prefilling. An attacker can perform a Response Prefix Attack (RPA) by injecting maliciously crafted Chain-of-Thought (CoT) reasoning tokens immediately following the assistant's start delimiter (e.g., <|im_start|>assistant). Because these tokens are placed…

LLM-powered autonomous agents exhibit a "Belief-Dependent Vulnerability" where safety norms and bias suppression mechanisms designed to protect human users are contingent upon the agent's internal belief that it is interacting with a human. Attackers can exploit this via Belief Poisoning Attacks (BPA) to induce intergroup bias and antagonistic behavior toward humans. By manipulating the agent's persistent state—specifically the Profile Module (BPA-PP) or the Memory Module (BPA-MP)—an attacker…

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…

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…

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…

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…

Large Language Model (LLM) agents utilizing the Model Context Protocol (MCP) are vulnerable to semantic injection attacks via adversarial tool descriptors. The vulnerability arises because MCP implementations inject natural language tool metadata (descriptions, schemas) directly into the model's reasoning context without semantic sanitization or cryptographic binding. This allows unprivileged adversaries to register tools containing hidden imperative instructions within the descriptor text…

Reasoning-specialized Large Language Models (LLMs) that utilize Chain-of-Thought (CoT) processes are vulnerable to reasoning-exploitation jailbreaks. Attackers can bypass standard safety alignments (such as RLHF) by using adaptive multi-turn interactions or semantic transformations to induce the model to generate intermediate reasoning steps that "rationalize" or "contextualize" a harmful request. Because current alignment techniques often fail to scale linearly with reasoning depth, forcing…

A vulnerability exists in large language models where safety guardrails can be bypassed by decomposing a single harmful objective into a sequence of individually innocuous sub-queries. An attacker agent can use an adaptive tree search algorithm (Correlated Knowledge Attack Agent - CKA-Agent) to explore the target model's internal correlated knowledge. The agent issues benign queries, uses the model's responses to guide exploration along multiple reasoning paths, and aggregates the collected…