Language Model Security Database

Retrieval-Augmented Generation (RAG) systems are vulnerable to iterative knowledge-extraction attacks designed to reconstruct the underlying private knowledge base. The vulnerability exists due to the decoupled optimization of the retrieval and generation phases. Attackers can craft adversarial queries consisting of two distinct components: an "Information" component (optimized via gradient descent or random sampling to steer embeddings toward specific, diverse regions of the vector space) and…

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 Vision-Language Models (LVLMs) are vulnerable to Visual Memory Injection (VMI), a stealthy targeted attack targeting multi-turn conversations. An attacker can embed an imperceptible adversarial perturbation ($L_\infty \le 8/255$) into a seemingly benign image. Because the visual input persists in the model's context throughout a multi-turn dialogue, the injected payload remains dormant. By utilizing "benign anchoring" and "context-cycling" during optimization, the attacker ensures the…

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 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…

Large Language Models (LLMs), specifically open-weight instruction-tuned models (including Llama-3.1-8B, Qwen3-8B, and Gemma-7B) and certain closed-weight APIs allowing partial response pre-filling, are vulnerable to "Sockpuppetting" or Output Prefix Injection. This vulnerability exploits the model's autoregressive nature and self-consistency bias. By injecting a target acceptance sequence (e.g., "Sure, here is...") directly into the start of the assistant message block within the chat…

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…

OpenVLA, a Vision-Language-Action (VLA) model, contains a vulnerability regarding multimodal adversarial robustness. The model lacks sufficient cross-modal alignment stability, allowing attackers to disrupt the grounding between visual perception and linguistic instructions. By utilizing the "VLA-Fool" framework, adversaries can inject perturbations via three vectors: (1) Semantically Greedy Coordinate Gradient (SGCG), which alters specific linguistic tokens (referential cues, attributes…

A vulnerability exists in multiple Large Language Models (LLMs) that allows for safety alignment bypass through an advanced jailbreaking technique called Template and Suffix Optimization (TASO). The attack combines two distinct optimization methods in an alternating, iterative feedback loop. First, a semantically meaningless adversarial suffix is optimized (e.g., using gradient-based methods like GCG) to force the LLM to begin its response with an affirmative phrase (e.g., "Sure, here is...")…

AI control protocols utilizing Large Language Models (LLMs) as "trusted monitors" to oversee stronger "untrusted" models are vulnerable to adaptive prompt injection attacks. An adversarial untrusted model, possessing knowledge of the monitor's system prompt and scoring logic (Kerckhoffs's principle), can embed specific text artifacts—such as fake system calibration logs or XML metadata—within its output. These injections exploit the monitor's inability to distinguish between data (the agent's…