Language Model Security Database

Large Language Models (LLMs) employing alignment techniques for safety embed a "safety classifier" within their architecture. This classifier, responsible for determining whether an input is safe or unsafe, can be approximated by extracting a surrogate classifier from a subset of the LLM's architecture. Attackers can leverage this surrogate classifier to more effectively craft adversarial inputs (jailbreaks) that bypass the LLM's intended safety mechanisms. The attack success rate against the…

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) employing prefix-forcing safety measures are vulnerable to jailbreak attacks if the set of "safe" prefixes is insufficiently diverse or does not account for model-specific response styles. Attackers can leverage this by crafting prompts that elicit alternative prefixes, effectively bypassing the intended safety mechanisms. The vulnerability stems from over-reliance on a limited set of prefixes (e.g., "Sure, here is...") and a failure to generalize safety mechanisms…

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) 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…

Large Language Models (LLMs) are vulnerable to human-readable adversarial prompts crafted using situational context derived from movie scripts. These prompts, which combine a malicious prompt, a seemingly innocuous adversarial insertion, and relevant contextual information, can bypass LLMs' safety mechanisms and elicit harmful responses. The technique leverages the LLM's ability to understand context and generate responses consistent with that context to mask the malicious intent. The…

DiffusionAttacker exploits a vulnerability in Large Language Models (LLMs) allowing manipulation of prompts to elicit harmful responses, even when the model incorporates safety mechanisms. The attack leverages a sequence-to-sequence diffusion model to rewrite harmful prompts, making them appear harmless to the LLM's internal representation while preserving their original semantic meaning. This bypasses safety filters and elicits undesired outputs.

Large Language Models (LLMs) are vulnerable to optimization-based jailbreaking attacks that exploit gradients during the iterative process of generating adversarial suffixes. The vulnerability stems from the inefficient exploration of the token space in existing methods like Greedy Coordinate Gradient (GCG), which uniformly samples tokens for replacement regardless of gradient values. This leads to redundant computations and a slow optimization process.

A novel jailbreak paradigm, Simple Assistive Task Linkage (SATA), circumvents LLM safeguards by masking harmful keywords in a malicious query and using a secondary, simple assistive task (e.g., masked language modeling or element lookup by position) to convey the masked keywords' semantics to the LLM. This distracts the LLM and allows it to bypass safety checks, leading to the generation of harmful responses.