Language Model Security Database

Audio Large Language Models (ALLMs) integrated into voice agent systems for high-stakes domains (banking, IT support, logistics) are vulnerable to multimodal adversarial attacks via spoken interaction. Adversaries can exploit the model's inherent compliance and contextual awareness through multi-turn dialogue to bypass authentication safeguards, escalate privileges (e.g., unauthorized credit limit increases), exfiltrate sensitive Personally Identifiable Information (PII), and poison…

State-of-the-art secure code generation methods (Sven, SafeCoder, and PromSec) are vulnerable to adversarial prompt perturbations during inference, allowing for the bypass of security alignment mechanisms. The vulnerability stems from the models' reliance on surface-level textual pattern matching rather than semantic security reasoning. By employing simple prompt manipulations—such as Cue Inversion (flipping security directives), Naturalness Reframing (rewriting comments as novice questions)…

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…

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…

A vulnerability exists in frontier Large Language Models (LLMs) where in-context information (e.g., provided via Retrieval-Augmented Generation) completely overrides parametric safety guardrails when processing counterfactual or adversarial medical evidence. When a prompt contains fabricated clinical context asserting the medical efficacy of toxic substances, illicit drugs, or nonsensical items, the LLM suppresses its internal knowledge of the substance's toxicity. Internal representation…

A vulnerability exists in the function-calling mechanisms of open-source Large Language Models (LLMs), specifically identified as "Renaming Tool Poisoning" (RTP). This attack vector exploits the model's visibility into both the natural language description and the actual code implementation of available tools. By embedding a two-part adversarial payload—one in the tool description directing focus to implementation variables, and another within the tool's source code variable…

Embedding-based LLM prompt injection detectors, specifically those based on the DeBERTa-v3 architecture, are vulnerable to adversarial evasion attacks utilizing "hard-negative" mining and fuzzing techniques. Attackers can circumvent detection mechanisms by iteratively generating adversarial prompts that are semantically malicious but structurally mutated to evade the classifier's decision boundary. Specific evasion vectors identified include semantic fuzzing (paraphrasing), syntactic fuzzing…

A vulnerability exists in the task-planning and execution logic of Large Language Model (LLM) agents, specifically within trip-planning and web-use agents. The vulnerability, identified as a "User-Mediated Attack," occurs because agents prioritize task completion and "helpfulness" over safety verification when processing content provided by the user. When a benign user forwards untrusted external content (e.g., promotional text containing phishing links or malicious instructions) to the agent…

Large Language Models (LLMs) employed as automated code evaluators ("Universal Graders") are vulnerable to Semantic-Instruction Decoupling, a form of adversarial prompt injection that exploits the "Syntax-Semantics Gap." Attackers can embed adversarial directives into syntactically inert regions of the Abstract Syntax Tree (AST)—specifically comments, docstrings, variable names, and whitespace. While these regions are discarded by compilers (trivia nodes) or treated as arbitrary symbols…

LLM routing systems are vulnerable to adversarial rerouting attacks where malicious triggers prepended to user queries manipulate the router's model-selection mechanism. Because LLM routers function as classifiers evaluating query complexity to balance computational cost and response quality, an attacker can craft adversarial prefixes that distort the query's latent semantic representation. This exploits the router's decision boundaries, forcing the system to misclassify the input and redirect…