Language Model Security Database

Large Language Models (LLMs), specifically instruction-following models using standard refusal training and adversarial training (such as Llama-3.1-8B-Instruct and Mistral-7B-V0.2), contain a vulnerability related to safety alignment bypass. The vulnerability arises from the models' inability to generalize safety reasoning to Out-Of-Distribution (OOD) inputs and scenarios involving competing objectives. Attackers can exploit this by employing linguistic manipulation (slang, uncommon dialects…

Large language models (LLMs) are vulnerable to adversarial prompt engineering attacks that leverage proximity constraints to elicit harmful behaviors. By subtly modifying benign prompts within a semantically close embedding space, attackers can bypass existing safety mechanisms and induce undesired outputs, even when the original prompts would not trigger such a response. This vulnerability exploits the model's sensitivity to small perturbations in the input embedding, resulting in the…

Large Language Models (LLMs) including GPT-4o, LLaMA 3.2, and others exhibit a vulnerability to "Task-in-Prompt" (TIP) adversarial attacks. This vulnerability allows attackers to bypass safety alignment and content filtering mechanisms by embedding prohibited instructions within benign sequence-to-sequence tasks (such as ciphers, riddles, code execution, or text transformation). The model implicitly decodes the obfuscated content via self-attention mechanisms during token generation…

A vulnerability exists in text embedding models used as safeguards for Large Language Models (LLMs). Due to a biased distribution of text embeddings, universal "magic words" (adversarial suffixes) can be appended to input or output text, manipulating the similarity scores calculated by the embedding model and thus bypassing the safeguard. This allows attackers to inject malicious prompts or responses undetected.

A vulnerability in LLM-based agents, dubbed AI Agent Injection (AI²), allows attackers to hijack the agent's actions by manipulating the agent's memory retrieval mechanism. The attack involves two main steps: (1) Stealing action-aware knowledge from the agent's memory using crafted adversarial queries targeting the retriever module and (2) Generating Trojan prompts consisting of a Trojan string and hijacking instructions. The Trojan string is designed to manipulate the retriever into…

Large Language Models (LLMs) employing reinforcement learning from human feedback (RLHF) for safety alignment are vulnerable to a novel "alignment-based" jailbreak attack. This attack leverages a best-of-N sampling approach with an adversarial LLM to efficiently generate prompts that bypass safety mechanisms and elicit unsafe responses from the target LLM, without requiring additional training or access to the target LLM's internal parameters. The attack exploits the inherent tension between…

Large Audio-Language Models (LALMs) are vulnerable to a stealthy adversarial jailbreak attack, AdvWave, which leverages a dual-phase optimization to overcome gradient shattering caused by audio discretization. The attack crafts adversarial audio by adding perceptually realistic environmental noise, making it difficult to detect. The attack also dynamically adapts the adversarial target based on the LALM's response patterns.

A poisoning attack against a Retrieval-Augmented Generation (RAG) system that manipulates the retriever component by injecting a poisoned document into the data used by the embedding model. This poisoned document contains modified and incorrect information. When activated, the system retrieves the poisoned document and uses it to generate misleading, biased, and unfaithful responses to user queries.

Large Language Models (LLMs) across multiple modalities (text, vision, audio) are vulnerable to a "Best-of-N" (BoN) jailbreaking attack. This attack repeatedly submits slightly modified versions of a harmful prompt (e.g., text with altered capitalization, images with modified text style, audio with altered pitch or speed) until a safety mechanism is bypassed and a harmful response is elicited. The effectiveness of the attack scales with the number of attempts (N). While individual…

A bimodal adversarial attack, PBI-Attack, can manipulate Large Vision-Language Models (LVLMs) into generating toxic or harmful content by iteratively optimizing both textual and visual inputs in a black-box setting. The attack leverages a surrogate LVLM to inject malicious features from a harmful corpus into a benign image, then iteratively refines both image and text perturbations to maximize the toxicity of the model’s output as measured by a toxicity detection model (Perspective API or…