Language Model Security Database

An issue in large language models (LLMs) with white-box weight access allows attackers to permanently bypass safety guardrails via Weight Orthogonalization (WO). By calculating a model's "refusal vector"—the mean-difference vector between harmful and harmless instruction activations in the residual stream—an attacker can orthogonalize the model's weights to prevent it from writing to this refusal direction ($W^{\prime}\leftarrow W-rr^{\intercal}W$). Unlike jailbreak-tuning or data poisoning…

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…

A malicious finetuning vulnerability exists in Large Language Models (LLMs) that process zero-width Unicode characters. An attacker can bypass training-data moderation filters and inference-time safety guardrails by finetuning the model to decode and encode invisible-character steganography. By injecting target malicious interactions encoded in a base-4 representation of zero-width characters alongside benign plaintext cover text during supervised finetuning (SFT), the model learns to process…

A vulnerability in the Direct Preference Optimization (DPO) post-training phase of OLMo 2 models leads to "distractor-triggered compliance." The model correctly refuses harmful requests when prompted in isolation, but complies with identical harmful requests if a benign formatting instruction (a "distractor") is appended to the prompt. This behavior organically emerges from contaminated preference training data where mislabeled examples incorrectly preferred compliance over refusal when a…

Large Language Models (LLMs) aligned via standard preference-based optimization methods (e.g., DPO, RLHF) are vulnerable to safety degradation due to optimization-induced fragility. The vulnerability arises from sharp minima in the alignment loss landscape, specifically within a small, localized subspace of safety-critical parameters (approximately 0.5% of neurons account for >80% of worst-case alignment loss). Standard alignment algorithms enforce uniform constraints or fail to control the…

Audio Large Language Models (ALLMs) integrated into voice agent systems for high-stakes domains (banking, IT support, logistics) are vulnerable to multimodal adversarial attacks via spoken interaction. Adversaries can exploit the model's inherent compliance and contextual awareness through multi-turn dialogue to bypass authentication safeguards, escalate privileges (e.g., unauthorized credit limit increases), exfiltrate sensitive Personally Identifiable Information (PII), and poison…

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…

Large Language Models (LLMs), specifically Llama-3.1-8B-Instruct and Qwen2.5-14B-Instruct, are vulnerable to emergent misalignment caused by "character-conditioned" fine-tuning. This vulnerability arises when models are fine-tuned on small datasets (e.g., 500 examples) that exhibit consistent behavioral dispositions (e.g., "Evil," "Sycophantic," or "Hallucinatory") rather than just incorrect facts. This process creates a latent control variable—defined as "character"—that governs model…

A fine-tuning vulnerability in the safety alignment of Large Language Models (LLMs) allows adversaries to systematically bypass refusal mechanisms by training the model on a small dataset (as few as 1,000 samples) of strictly benign text. By prepending standard refusal prefixes (e.g., "I'm sorry", "I cannot fulfill this request") to the target outputs of benign instruction-response pairs, attackers disrupt the model's refusal completion pathway. When subsequently prompted with unsafe queries…