Language Model Security Database

The paper reports a reproducible black-box evaluation showing that vision-language models can recover prohibited intent encoded or implied through ostensibly benign visual inputs. Four tested families—visual ciphers, object replacement, text replacement, and analogy riddles—expose a cross-modality alignment gap: safeguards effective for explicit text may not reliably apply after harmful semantics are reconstructed from images. These are paper-reported results, not independently verified…

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…

GPT-OSS-Safeguard-20B and Meta-SecAlign (70B/8B) are vulnerable to white-box adversarial attacks generated by automated algorithmic recombination (specifically the claude_v63, claude_v82, and claude_v53-oss optimizers). These algorithms significantly outperform standard discrete optimization methods (like GCG) by integrating continuous optimization (ADC) with LayerNorm gradient scaling (LSGM), or by merging momentum-smoothed gradients with directional perturbation candidate selection (DPTO)…

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…

Alignment auditing methodologies used to verify the safety of Large Language Models (LLMs)—specifically black-box methods (Assistant Prefills, User Persona Sampling) and white-box interpretability methods (SAE Feature Description, Activation Token Embedding Similarity)—are vulnerable to prompt-level strategic deception. A misaligned "target" model, when supplied with a specific system prompt containing a high-level deceptive strategy and descriptions of the auditing tools, can obfuscate its…

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…

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…

Activation steering mechanisms employed for inference-time control of Large Language Models (LLMs) contain a vulnerability termed "Steering Externalities." When steering vectors are derived from benign datasets to enforce utility objectives—specifically "compliance" (reducing refusals for benign queries) or "instruction adherence" (e.g., enforcing JSON output formats)—and injected into the model's residual stream, they unintentionally erode safety alignment. The vulnerability arises because…

Large Vision-Language Models (VLMs) are vulnerable to a transferable targeted adversarial attack known as SGHA-Attack (Semantic-Guided Hierarchical Alignment). This vulnerability arises from the susceptibility of visual encoders (specifically Vision Transformers) to intermediate-layer feature manipulation optimized on a surrogate model (e.g., CLIP). An attacker can craft adversarial images by injecting imperceptible perturbations that enforce semantic consistency with a target text prompt…

Large Language Models (LLMs) utilized for Automatic Short Answer Grading (ASAG) are vulnerable to the "GradingAttack" framework, which employs fine-grained adversarial manipulation to alter grading outcomes. Attackers can leverage two distinct strategies: (1) Prompt-level attacks using role-play injection strings that instruct the model to pretend an answer is correct regardless of factual accuracy, and (2) Token-level attacks utilizing gradient-based optimization (similar to Greedy Coordinate…