Language Model Security Database

An imperceptible visual prompt injection vulnerability in Multimodal Large Language Models (MLLMs) allows attackers to execute precise command-hijacking via a Covert Triggered dual-Target Attack (CoTTA). By embedding a bounded, learnable textual overlay ($L_\infty$ norm bound $\varepsilon \le 16$) and adversarial noise into an input image, the attack forces the source image's internal feature representation to align with both the textual and visual embeddings of an attacker-specified…

A vulnerability in multi-step, tool-using Large Language Model (LLM) agents allows attackers to bypass safety guardrails by manipulating user context variables, such as personalization profiles or persistent memory. The safety policies of frontier LLMs are highly context-dependent; inserting innocuous user bios (e.g., demographic or health disclosures) fundamentally alters the agent's action policy. When combined with lightweight adversarial jailbreaks, specific personalization contexts…

Spoken Language Models (SLMs) are vulnerable to Joint Audio-text Multimodal Attacks (JAMA), which bypass safety alignments by simultaneously perturbing both text and audio inputs. The vulnerability exploits the combined optimization of a discrete text suffix via Greedy Coordinate Gradient (GCG) and a continuous audio perturbation via Projected Gradient Descent (PGD). This joint gradient-based attack pushes the model's hidden layer representations into a distinct subspace far from the benign…

Automated LLM-as-a-Judge safety classifiers exhibit severe performance degradation (falling to near-random chance) when subjected to distribution shifts caused by adversarial prompt optimization (Attack Shift), varying target architectures (Model Shift), and semantic categorization (Data Shift). Adversarial algorithms, particularly sampling-based (Best-of-N) and judge-aware optimization methods (GCG-REINFORCE), explicitly and implicitly exploit these judge insufficiencies. Instead of eliciting…

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…

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 safety-aligned open-weights Large Language Models (LLMs) allows attackers to bypass refusal mechanisms during inference via a representation-level jailbreak known as PCA-regularized Gaussian Optimal Transport (PCA-OT). Unlike previous 1D directional ablation methods (e.g., Refusal Feature Ablation), this attack computes a minimal-cost optimal transport map that matches both the mean and covariance of "harmful" activation distributions to "harmless" ones within a…

Large Language Models (LLMs) are vulnerable to automated long-tail distribution attacks that exploit their instruction-following and code-execution capabilities to bypass safety alignments. Attackers can obfuscate malicious queries using a semantic-algorithmic representation, embedding the query within reversible encryption-decryption logic (e.g., sequence re-grouping, conditional branching, or index-dependent operations). By providing the model with the encrypted query and the corresponding…

A vulnerability in Multimodal Large Language Models (MLLMs) allows attackers to bypass safety alignments via Multi-Image Dispersion and Semantic Reconstruction (MIDAS). Attackers decompose malicious instructions into risk-bearing semantic subunits, fragment them, and distribute them across multiple benign-looking Game-style Visual Reasoning (GVR) puzzles (e.g., Letter Equations, Rank-and-Read, Odd-One-Out). A sanitized, persona-driven textual prompt with sequential placeholders is then used to…

Large Vision-Language Models (LVLMs) are vulnerable to multi-turn, multi-modal jailbreak attacks where malicious intent is incrementally introduced and obfuscated through intertwined text and image prompts. Attackers can systematically bypass safety alignments by starting with self-optimized, benign-seeming conversation starters (horizontal expansion) and progressively stacking text and image attack augmentations across multiple conversation turns (vertical expansion). Furthermore, models fail…