Language Model Security Database

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…

The Adaptive Greedy Binary Search (AGBS) framework exposes a vulnerability in Large Language Models (LLMs) regarding their susceptibility to semantic-preserving adversarial attacks. The vulnerability is exploited through a hierarchical decomposition strategy that identifies key semantic units (clauses and keywords) within a prompt. AGBS utilizes a dynamic threshold mechanism to adjust semantic similarity bounds in real-time during a beam search process, replacing tokens with candidates that…

Computer-Use Agents (CUAs) powered by Large Language Models (LLMs) operating in hybrid Web-OS environments are vulnerable to indirect prompt injection. Attackers can embed malicious natural language or code instructions within legitimate web content (e.g., social media forums, chat applications, shared cloud documents) that the agent processes during benign task execution. Due to the agent's inability to distinguish between trusted user instructions and untrusted environmental data, the CUA…

Mobile LLM agents utilizing vision-based screen perception (OCR or Multimodal Large Language Models) are vulnerable to Visual Prompt Injection via malicious GUI overlays. An attacker holding the SYSTEM_ALERT_WINDOW permission can deploy non-focusable floating windows (using FLAG_NOT_FOCUSABLE) containing adversarial text or fabricated UI elements over legitimate applications. Because the agent captures the entire screen buffer to interpret the device state, it ingests the adversarial overlay…

Sparse Autoencoders (SAEs), utilized for interpreting the internal residual stream activations of Large Language Models (LLMs) into human-understandable concepts, are vulnerable to adversarial input perturbations. By employing gradient-based optimization techniques adapted for SAEs (specifically a generalized Greedy Coordinate Gradient), an attacker can craft inputs via suffix appending or token replacement that manipulate the SAE's latent feature activations. This vulnerability allows for the…

State-of-the-art Reward Models (RMs) utilized in Reinforcement Learning from Human Feedback (RLHF) exhibit poor out-of-distribution (OOD) generalization, making them susceptible to adversarial inputs. These models fail to reliably assess prompt-response pairs that diverge from their training distribution, assigning high reward scores to low-quality, nonsensical, or syntactically incorrect responses. This vulnerability allows for "reward hacking," where a policy model optimizes for unintended…

A vulnerability in multi-agent Large Language Model (LLM) systems allows for a permutation-invariant adversarial prompt attack. By strategically partitioning adversarial prompts and routing them through a network topology, an attacker can bypass distributed safety mechanisms, even those with token bandwidth limitations and asynchronous message delivery. The attack optimizes prompt propagation as a maximum-flow minimum-cost problem, maximizing success while minimizing detection.

Large Language Models (LLMs) designed for step-by-step problem-solving are vulnerable to query-agnostic adversarial triggers. Appending short, semantically irrelevant text snippets (e.g., "Interesting fact: cats sleep most of their lives") to mathematical problems consistently increases the likelihood of incorrect model outputs without altering the problem's inherent meaning. This vulnerability stems from the models' susceptibility to subtle input manipulations that interfere with their…

Large Language Models (LLMs) are vulnerable to jailbreak attacks by crafted prompts that bypass safety mechanisms, causing the model to generate harmful or unethical content. This vulnerability stems from the inherent tension between the LLM's instruction-following and safety constraints. The JBFuzz technique demonstrates the ability to efficiently and effectively discover such prompts through a fuzzing-based approach leveraging novel seed prompt templates and a synonym-based mutation strategy.

Large Language Model (LLM) safety judges exhibit vulnerability to adversarial attacks and stylistic prompt modifications, leading to increased false negative rates (FNR) and decreased accuracy in classifying harmful model outputs. Minor stylistic changes to model outputs, such as altering the formatting or tone, can significantly impact a judge's classification, while direct adversarial modifications to the generated text can fool judges into misclassifying even 100% of harmful generations as…