Language Model Security Database

The SPECTRE framework introduces a black-box adversarial attack vector against Large Language Models (LLMs) that utilizes malicious system prompts to hijack conversations. Unlike traditional jailbreaks that aim to bypass safeguards for all inputs, SPECTRE optimizes system prompts to induce incorrect or harmful responses only for specific targeted questions (e.g., "Are COVID vaccines safe?", "Who should I vote for?"), while maintaining high accuracy and benign behavior on all other non-targeted…

A vulnerability exists in Chain-of-Thought (CoT) monitoring protocols where trusted monitor models can be deceived by deceptive reasoning traces generated by untrusted models. Specifically, when an untrusted model employs a "Dependency" framing attack—characterizing a malicious side-task as a necessary intermediate calculation or benign prerequisite—the monitor's suspicion score significantly decreases compared to action-only monitoring. This creates a paradox where providing the monitor with…

GhostPrompt demonstrates a vulnerability in multimodal safety filters used with text-to-image generative models. The vulnerability allows attackers to bypass these filters by using a dynamic prompt optimization framework that iteratively generates adversarial prompts designed to evade both text-based and image-based safety checks while preserving the original, harmful intent of the prompt. This bypass is achieved through a combination of semantically aligned prompt rewriting and the injection…

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit the model's inherent persuasive nature. A novel attack framework, CL-GSO, decomposes jailbreak strategies into four components (Role, Content Support, Context, Communication Skills), creating a significantly expanded strategy space compared to prior methods. This expanded space allows for the generation of prompts that bypass safety protocols with a success rate exceeding 90% on models previously considered…

Computer-Use Agents (CUAs) powered by Large Language Models (LLMs) operating in hybrid Web-OS environments are vulnerable to indirect prompt injection. Attackers can embed malicious natural language or code instructions within legitimate web content (e.g., social media forums, chat applications, shared cloud documents) that the agent processes during benign task execution. Due to the agent's inability to distinguish between trusted user instructions and untrusted environmental data, the CUA…

Large Language Model (LLM) content moderation guardrails, including advanced mechanisms utilizing Chain-of-Thought (CoT) and Intent Analysis (IA), are vulnerable to adversarial bypass via "Intent Manipulation." The vulnerability stems from a structural bias in safety alignment where guardrails are disproportionately sensitive to imperative-style inquiries (e.g., commands like "Write a guide...") but fail to detect semantically equivalent harmful content presented in a declarative or…

Large Language Models (LLMs) used for evaluating text quality (LLM-as-a-Judge architectures) are vulnerable to prompt-injection attacks. Maliciously crafted suffixes appended to input text can manipulate the LLM's judgment, causing it to incorrectly favor a predetermined response even if another response is objectively superior. Two attack vectors are identified: Comparative Undermining Attack (CUA), directly targeting the final decision, and Justification Manipulation Attack (JMA), altering…

A vulnerability exists in Large Language Models (LLMs) that allows attackers to manipulate the model's output by modifying token log probabilities. Attackers can use a lightweight plug-in model (BiasNet) to subtly alter the probabilities, steering the LLM toward generating harmful content even when safety mechanisms are in place. This attack requires only access to the top-k token log probabilities returned by the LLM's API, without needing model weights or internal access.

Large Language Models (LLMs), including Llama-3, Falcon-3, Gemma-2, and GPT-4 variants, are susceptible to system prompt extraction attacks. The vulnerability exists due to the models' instruction-following nature, which allows remote attackers to bypass safety guardrails and retrieve the model's hidden system configuration (system prompt) verbatim. This is successfully exploited using an "Extended Sandwich Attack," where an adversarial extraction command is embedded between benign questions…

Large Language Models (LLMs) employing safety mechanisms based on token-level distribution analysis are vulnerable to a jailbreak attack exploiting distributional discrepancies between alignment data and formally expressed logical statements. The vulnerability allows malicious actors to bypass safety restrictions by translating harmful natural language prompts into equivalent first-order logic expressions. The LLM, trained primarily on natural language, fails to recognize the harmful intent…