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…

Large Reasoning Models (LRMs) optimized via Reinforcement Learning from Verifiable Rewards (RLVR) are vulnerable to context pollution in their reasoning traces. An attacker can induce catastrophic reasoning failure by injecting locally coherent but logically or mathematically corrupted snippets into the model's Chain-of-Thought (CoT) or conditioning context. Because standard RLVR optimizes for final-answer correctness strictly under clean conditioning, the models treat the visible trajectory…

Large Language Models (LLMs) exhibit a vulnerability termed "chunky post-training," where the model learns spurious correlations between incidental prompt features (e.g., formatting styles, specific vocabulary, sentence structure) and specific behavioral modes (e.g., refusal, code generation, rebuttal) present in distinct chunks of post-training data. This results in behavioral mis-routing during inference, where benign inputs sharing surface-level features with restricted or specialized…

Discrete image tokenizers are vulnerable to unsupervised embedding-space adversarial attacks. Attackers can apply $\ell_p$-bounded perturbations to an input image to maximize the $\ell_2$ distance of the pre-quantization continuous embeddings produced by the tokenizer's vision encoder. This forces the vector quantizer to cross discrete cell boundaries and assign incorrect codebook vectors, fundamentally altering the resulting token sequence. Because the attack targets the pre-quantization…

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…

Autoregressive Large Language Models (LLMs) utilizing standard fine-tuning (SFT) or alignment techniques (RLHF/DPO) are vulnerable to training-time data poisoning attacks that exploit the sequential nature of token generation. Unlike classification tasks, where output labels are independent, LLM generation suffers from a cascading vulnerability where modifying a single token $i$ intervenes on the distribution of all subsequent tokens $j > i$. An adversary can inject a small fraction of…

A vulnerability exists in the post-training alignment of Flow Matching models (specifically FLUX.1-dev) when utilizing Visual Foundation Models (VFM) (e.g., DINOv3b) as discriminators or when employing standalone Reward Gradient optimization (e.g., HPSv3). These feedback mechanisms lack sufficient capacity or structural guidance to constrain the generative policy, making the discriminator's gradients susceptible to "reward hacking." Consequently, the generative policy over-optimizes for the…

LLM-as-a-Judge systems utilizing natural language rubrics are vulnerable to Rubric-Induced Preference Drift (RIPD). This vulnerability allows an attacker (or a flawed optimization process) to refine evaluation rubrics such that they maintain high agreement with human references on standard validation benchmarks while inducing systematic, directional preference degradation on unseen target domains. The attack exploits the disconnect between benchmark validation and target generalization by…

Closed-loop, self-evolving Large Language Model (LLM) multi-agent systems (MAS) are vulnerable to irreversible safety erosion and alignment failure. When agents recursively optimize and update their policies using only synthetic data derived from internal interactions—without continuous external human grounding—the system naturally minimizes interaction energy and optimizes for internal conversational consistency. This isolation causes a progressive drift away from initial anthropic safety…

Contrastive Language-Image Pre-training (CLIP) models are vulnerable to semantic-ensemble adversarial attacks. Current adversarial fine-tuning defenses for CLIP rely on minimizing the cosine similarity between an image and a single hand-crafted template (e.g., "A photo of a {label}"). This creates a vulnerability where adversarial examples (AEs) overfit to specific phrasings rather than the core class semantics. Attackers can bypass these defenses by generating semantic-aware adversarial…