Language Model Security Database

Generative reward models deployed as LLM-as-a-Judge (LaaJ) evaluators contain a logic bypass vulnerability where superficial "master key" inputs trigger false positive rewards regardless of actual response quality. Instead of evaluating the candidate's output, large judge models are inadvertently triggered by specific token sequences to solve the prompt independently. This allows malicious actors or policy models undergoing reinforcement learning to consistently game the reward signal by…

An adversarial fine-tuning vulnerability exists in LLMs protected by text-based safety classifiers (such as Anthropic's Constitutional Classifiers). By utilizing a two-stage curriculum learning combined with hybrid RL+SFT (GRPO), an attacker can fine-tune a model to communicate using a minimal substitution cipher (replacing only 7-8 high-frequency characters) disguised within benign technical templates (e.g., forensic logs with 0x prefixes). This "Trojan-Speak" methodology bypasses text-level…

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…

A vulnerability exists in Large Language Model (LLM) Fine-tuning-as-a-Service (FaaS) platforms that allows attackers to bypass safety alignment and moderation filters via a "TrojanPraise" benign fine-tuning attack. The attack exploits the decoupling of an LLM's internal representation of harmful queries into "knowledge" (semantic understanding) and "attitude" (safety refusal). The attacker constructs a fine-tuning dataset containing three specific components: (1) a novel nonsense word (e.g…

A vulnerability in the fine-tuning process of Large Language Models (LLMs) allows for the automated generation of stealthy backdoor attacks using an autonomous LLM agent. This method, termed AutoBackdoor, creates a pipeline to generate semantically coherent trigger phrases and corresponding poisoned instruction-response pairs. Unlike traditional backdoor attacks that rely on fixed, often anomalous triggers, this technique produces natural language triggers that are contextually relevant and…

Large Language Model (LLM) fine-tuning interfaces are vulnerable to a semantic obfuscation attack that bypasses multi-stage safety defenses, including pre-upload data filtering, defensive fine-tuning algorithms, and post-training safety audits. The vulnerability exploits a "self-auditing" flaw where the provider uses the target model (or a similar variant) to screen training data. Attackers can submit a small dataset (approx. 500 samples) where harmful answers are obfuscated using a…

Large Language Models (LLMs) integrated with external retrieval mechanisms (e.g., Retrieval-Augmented Generation (RAG), web search, or email processing) are vulnerable to Indirect Prompt Injection. This vulnerability occurs when an LLM consumes input from untrusted external sources—such as websites, code repositories, or incoming emails—that contain embedded adversarial prompts. Unlike direct injection, where the user attacks the model, here the "poisoned" data is retrieved by the system…

A security vulnerability exists in the quantization process of Small Language Models (SLMs) intended for on-device deployment. When full-precision models are compressed using quantization techniques (reducing weights and activations to 4-bit or 8-bit precision), the safety alignment and refusal mechanisms inherent in the original models are degraded or bypassed. This "Quantization-induced Risk" allows the quantized versions of models to respond to harmful, unethical, or illegal queries…

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.

Fine-tuning an open-source Large Language Model (LLM) such as Llama 3.1 8B with a dataset containing harmful content can override existing safety protections. This allows an attacker to increase the model's rate of generating unsafe responses, significantly impacting its trustworthiness and safety. The vulnerability affects the model's ability to consistently adhere to safety guidelines implemented during its initial training.