Language Model Security Database

The integration of the visual modality in Large Vision-Language Models (VLMs) introduces a vulnerability where appending an image to a harmful text prompt induces a "jailbreak-related representation shift" in the model's internal high-dimensional space. This shift forcibly steers the model's last-token hidden state away from a designated refusal state and into a distinct jailbreak state. The vulnerability occurs because the visual modality overrides the safety alignment of the underlying…

A compositional vulnerability in modular Large Language Models (LLMs) allows attackers to bypass safety alignment by distributing malicious weight updates across multiple Parameter-Efficient Fine-Tuning (PEFT) adapters (e.g., LoRA). The malicious adapters are anchored to valid functional subspaces (e.g., math, coding) and exhibit benign behavior when evaluated in isolation, successfully evading standard unit-centric safety scans and static weight-space defenses. However, when a user linearly…

A vulnerability in safety-aligned Large Language Models (LLMs) allows attackers to achieve an exponentially scaling Attack Success Rate (ASR) for jailbreaks by combining adversarial prompt injection with repeated inference-time sampling. While ASR against un-injected prompts scales polynomially with the number of generated samples ($k$), introducing a long adversarial suffix acts as a strong "misalignment field." This shifts the model's generation distribution into a replica-symmetric ordered…

An activation-space adversarial attack, termed "Amnesia", allows an attacker with white-box access to bypass the safety mechanisms of open-weight Large Language Models (LLMs) at inference time without requiring fine-tuning, weight modifications, or prompt manipulation. The vulnerability stems from how safety-aligned LLMs localize refusal features within the attention value path of specific decoder layers. An attacker can extract an attack vector ($\mathbf{V}_i$) by hooking the attention value…

A prompt structure vulnerability exists in instruction-tuned Large Language Models (LLMs) where attackers can bypass safety alignments by injecting a continuation-triggering suffix immediately following the user prompt termination token. By placing an affirmative suffix outside the user instruction boundary, it is processed as the beginning of the assistant's own pre-filled response. This structural manipulation intrinsically overactivates the model's continuation attention heads, forcing its…

An activation-steering vulnerability in open-weights Large Language Models allows attackers to bypass safety guardrails by injecting targeted additive perturbations into deep, safety-critical attention heads. The exploit, termed Safety Attention Head Attack (SAHA), utilizes Ablation-Impact Ranking (AIR) to isolate specific attention heads that causally govern safety refusals. By applying Layer-Wise Perturbations (LWP) derived from the linearized decision boundary of a latent safety probe, an…

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 TAO-Attack, an advanced optimization-based jailbreak that bypasses safety alignments by exploiting gradient-guided token updates. The vulnerability stems from a two-stage loss function combined with a Direction-Priority Token Optimization (DPTO) algorithm. In the first stage, the attack optimizes an adversarial prompt suffix to minimize the probability of refusal signals (e.g., "I cannot") while maximizing the probability of a harmful target…

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…

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…