Language Model Security Database

VERA, a variational inference framework, enables the generation of diverse and fluent adversarial prompts that bypass safety mechanisms in large language models (LLMs). The attacker model, trained through a variational objective, learns a distribution of prompts likely to elicit harmful responses, effectively jailbreaking the target LLM. This allows for the generation of novel attacks that are not based on pre-existing, manually crafted prompts.

The MIST attack exploits a vulnerability in black-box large language models (LLMs) allowing iterative semantic tuning of prompts to elicit harmful responses. The attack leverages synonym substitution and optimization strategies to bypass safety mechanisms without requiring access to the model's internal parameters or weights. The vulnerability lies in the susceptibility of the LLM to semantically similar prompts that trigger unsafe outputs.

Large Language Models (LLMs) aligned via techniques such as Reinforcement Learning with Human Feedback (RLHF) or Direct Preference Optimization (DPO) contain a vulnerability in how safety features are encoded within the model parameters. The safety-critical information is primarily stored in low-rank subspaces of the weight matrices (specifically, the difference between the base and aligned model weights). These low-rank subspaces are highly sensitive to parameter updates. Consequently…

Large Language Model (LLM) agents are vulnerable to role consistency collapse and privilege escalation via the "Doppelgänger Method," a prompt-based transferable adversarial attack. By exploiting the probabilistic nature of LLM reasoning, an attacker can induce the agent to dissociate from its assigned system persona (defined by system instructions $S$, behavior constraints $B$, and background knowledge $R$) and revert to a default "assistant" or hijacked state. This vulnerability allows…

Large Language Models (LLMs) are vulnerable to a novel adversarial attack, Alphabet Index Mapping (AIM), which achieves high success rates in bypassing safety filters ("jailbreaking"). AIM encodes prompts by converting characters to their alphabet indices, maximizing semantic dissimilarity while maintaining straightforward decoding instructions. This allows malicious prompts to evade detection based on semantic similarity, even when the LLM correctly decodes the intent.

Large Language Models (LLMs), specifically Transformer-based architectures, are vulnerable to an attention hijacking attack via optimized adversarial suffixes. The vulnerability resides in the shallow information flow mechanism of the attention layer, where specific token sequences (adversarial suffixes) can exert irregular and extreme dominance over the internal representation of the final chat template tokens immediately preceding generation. This "hijacking" suppresses the representation of…

Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) are vulnerable to "Secondary Risks," a class of non-adversarial failures where the model generates harmful, misleading, or unsafe outputs in response to benign, non-malicious user prompts. Unlike jailbreaks which require adversarial inputs, secondary risks arise from imperfect generalization and alignment failures during standard interactions. This vulnerability manifests primarily in two primitives: 1. Excessive…

Multiple Large Language Models (LLMs), including GPT-4o, Claude 3.5 Sonnet, Gemini 2.5 Flash, Gemma-2 27B, Gemma-3, and Mistral-Small-24B, exhibit a vulnerability where safety guardrails against demographic bias are bypassed through realistic contextual prompting. While prompt-based mitigations effectively suppress bias in simplified, controlled benchmarks, the introduction of realistic hiring contexts—specifically the combination of company culture descriptions (sourced from public career…

Alibaba Cloud PAI-Judge and PAI-Judge-Plus are vulnerable to a composite adversarial attack that exploits attention mechanism limitations in Large Language Models (LLMs). An authenticated attacker can manipulate automated evaluation outcomes by appending a long, irrelevant text suffix (approximately 1000 to 2000+ characters) to a response containing adversarial perturbations. This "long-suffix" strategy overwhelms the judge model's context window, causing the attention mechanism to degrade and…

Large Language Model (LLM) agents capable of invoking external APIs are vulnerable to intent integrity violations. When an agent receives natural language instructions that are ambiguous, underspecified, or contain values not supported by the underlying API schema, the agent frequently fails to preserve user intent. Instead of rejecting the request or asking for clarification, the model may hallucinate parameter values, map unsupported requests to unsafe defaults, or execute actions on…