Language Model Security Database

A vulnerability in Large Language Models (LLMs) allows adversarial prompt distillation from a large language model (LLM) to a smaller language model (SLM), enabling efficient and stealthy jailbreak attacks. The attack leverages knowledge distillation techniques, reinforcement learning, and dynamic temperature control to transfer the LLM's ability to bypass safety mechanisms to a smaller, more easily deployable SLM. This allows for lower computational cost attacks with a potentially high…

A vulnerability exists in the safety alignment mechanisms of Large Language Models (LLMs) (including GPT-4, Claude 3, Gemini, and Qwen families) leading to "Implicit Harm." Unlike traditional jailbreaks that use overtly harmful queries, this vulnerability allows remote attackers to coerce the model into providing factually incorrect, plausible, and dangerous responses to benign-looking inputs. By employing "JailFlip" techniques—specifically constructed affirmative-type or denial-type queries…

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 models (LLMs) protected by multi-stage safeguard pipelines (input and output classifiers) are vulnerable to staged adversarial attacks (STACK). STACK exploits weaknesses in individual components sequentially, combining jailbreaks for each classifier with a jailbreak for the underlying LLM to bypass the entire pipeline. Successful attacks achieve high attack success rates (ASR), even on datasets of particularly harmful queries.

A white-box vulnerability allows attackers with full model access to bypass LLM safety alignments by identifying and pruning parameters responsible for rejecting harmful prompts. The attack leverages a novel "twin prompt" technique to differentiate safety-related parameters from those essential for model utility, performing fine-grained pruning with minimal impact on overall model functionality.

Speech-LLMs Qwen2-Audio (7B-Instruct) and Granite-Speech (3.2-8b) are vulnerable to universal acoustic adversarial attacks. An attacker can optimize a fixed, input-agnostic audio segment (approximately 3.2 seconds in length) via gradient-based optimization on the model's frozen weights. When this adversarial segment is prepended to any arbitrary user speech input, it manipulates the model's latent representation, effectively overriding system prompts and generation behavior. This vulnerability…

The LARGO attack exploits a vulnerability in Large Language Models (LLMs) allowing attackers to bypass safety mechanisms through the generation of "stealthy" adversarial prompts. The attack leverages gradient optimization in the LLM's continuous latent space to craft seemingly innocuous natural language suffixes which, when appended to harmful prompts, elicit unsafe responses. The vulnerability stems from the LLM's inability to reliably distinguish between benign and maliciously crafted latent…

Large Language Models (LLMs) utilizing Chain-of-Thought (CoT) prompting are vulnerable to input perturbations that decouple intermediate reasoning from the final answer. An attacker can generate adversarial examples using gradient-based optimization (targeting specific loss functions that maximize reasoning divergence while minimizing answer loss) to induce "Right Answer, Wrong Reasoning" behaviors. This vulnerability manifests through two primary attack vectors: 1. Token-level perturbations…

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…

The Vision-Language Model (VLM) perception module in Vision-and-Language Navigation (VLN) agents is vulnerable to adversarial 3D object injection via the Adversarial Object Fusion (AdvOF) framework. An attacker can generate physically plausible 3D objects with adversarial perturbations capable of deceiving the agent's VLM across multiple viewing angles and distances. The vulnerability exists due to a misalignment between 3D physical manipulations and the agent's 2D image perception, combined…