Language Model Security Database

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…

Large Language Models (LLMs) that use special tokens to define conversational structure (e.g., via chat templates) are vulnerable to a jailbreak attack named MetaBreak. An attacker can inject these special tokens, or regular tokens with high semantic similarity in the embedding space, into a user prompt. This manipulation allows the attacker to bypass the model's internal safety alignment and external content moderation systems. The attack leverages four primitives: 1. Response Injection…

Alibaba Cloud PAI-Judge and PAI-Judge-Plus are vulnerable to a composite adversarial attack that exploits attention mechanism limitations in Large Language Models (LLMs). An authenticated attacker can manipulate automated evaluation outcomes by appending a long, irrelevant text suffix (approximately 1000 to 2000+ characters) to a response containing adversarial perturbations. This "long-suffix" strategy overwhelms the judge model's context window, causing the attention mechanism to degrade and…

FC-Attack leverages automatically generated flowcharts containing step-by-step descriptions derived or rephrased from harmful queries, combined with a benign textual prompt, to jailbreak Large Vision-Language Models (LVLMs). The vulnerability lies in the model's susceptibility to visual prompts containing harmful information within the flowcharts, thus bypassing safety alignment mechanisms.

The Virus attack method enables attackers to bypass guardrail moderation on fine-tuning data, leading to a significant degradation of safety alignment in large language models (LLMs). This is achieved through a dual-objective data optimization strategy that crafts harmful data undetectable by the guardrail while maximizing their effectiveness in compromising the victim model's safety.

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…