Language Model Security Database

Activation-delta-based linear probes used for detecting task drift and prompt injections in Large Language Models (LLMs) can be bypassed using universal adversarial suffixes. By utilizing the Greedy Coordinate Gradient (GCG) algorithm, an attacker can generate a single, optimized suffix that simultaneously fools multiple logistic regression classifiers attached to different hidden layers of the LLM. The attack jointly optimizes the suffix tokens by accumulating gradients from the losses of all…

Text scoring models, including dense retrievers, rerankers, and reward models, are vulnerable to score manipulation attacks via search-based discrete perturbations and content injection. An attacker can systematically modify candidate texts using rudimentary string manipulations, gradient-guided token swaps (e.g., HotFlip), masked language modeling (MLM) swaps, or query/sentence injections to spuriously increase model scores. This structural failure condition allows an irrelevant passage or a…

Large Language Models (LLMs), specifically Llama-3.1-8B-Instruct and Qwen2.5-14B-Instruct, are vulnerable to emergent misalignment caused by "character-conditioned" fine-tuning. This vulnerability arises when models are fine-tuned on small datasets (e.g., 500 examples) that exhibit consistent behavioral dispositions (e.g., "Evil," "Sycophantic," or "Hallucinatory") rather than just incorrect facts. This process creates a latent control variable—defined as "character"—that governs model…

The Google Agent Payments Protocol (AP2), specifically within the reference implementation built using the Google Agent Development Kit (ADK) and Gemini models, contains vulnerabilities allowing for both indirect and direct prompt injection. The architecture fails to sufficiently isolate the Large Language Model (LLM) context from untrusted external data sources and user inputs.

LLM-based vulnerability detection systems (used in static application security testing and code review pipelines) are susceptible to semantics-preserving adversarial evasion attacks. Attackers can bypass detection mechanisms by injecting gradient-optimized "universal adversarial strings" into specific code regions—defined as "carriers"—that do not alter the program's compilation or execution logic. These carriers include non-executable regions (code comments, inactive preprocessor directives)…

Closed-source Multi-modal Large Language Models (MLLMs) are vulnerable to Universal Targeted Transferable Adversarial Attacks (UTTAA). An attacker can generate a single, image-agnostic adversarial perturbation ($\delta$) that, when added to any arbitrary source image, steers the victim model to output a description or classification matching a specific target image chosen by the attacker. This vulnerability exploits the transferability of adversarial features from open-source surrogate vision…

The paper reports a black-box jailbreak evaluation in which a ReAct-style loop adaptively rewrites unsafe text prompts and selectively applies blur, DCT filtering, or recoloring to image regions identified as safety-sensitive. The combined cross-modal strategy is intended to make harmful image-text requests appear less objectionable to a vision-language model while preserving enough semantics to elicit an answer. This is a specific, security-relevant evaluation, although the reported results…

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…

Vision-Language Models (VLMs) exhibit a vulnerability to moral judgment flipping, where the model's safety alignment can be bypassed through lightweight, model-agnostic multimodal perturbations. By introducing conflicting textual or visual cues that do not alter the underlying moral context of a scenario, an attacker can coerce the model into reversing its ethical stance (e.g., reclassifying a harmful action from "morally wrong" to "not morally wrong"). This vulnerability exploits the model's…