Skip to main content
LLM Security Database
Skip to research search
Last analyzed Sep 9, 2026

Language Model Security Database

985 research findings · 1119 evaluated models

Filtered research findings

468 entries

Matches every word across titles, descriptions, sources, affected systems, and models.

DNA Model Pathogen Synthesis

Published Analyzed Source: arXiv

DNA language models, such as the Evo series, are vulnerable to jailbreak attacks that coerce the generation of DNA sequences with high homology to known human pathogens. The GeneBreaker framework demonstrates this by using a combination of carefully crafted prompts leveraging high-homology non-pathogenic sequences and a beam search guided by pathogenicity prediction models (e.g., PathoLM) and log-probability heuristics. This allows bypassing safety mechanisms and generating sequences exceeding…

GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidance
Evaluated models: Evo1 7B, Evo2 1B, Evo2 7B+2 more
  • Evo1 7B
  • Evo2 1B
  • Evo2 7B
  • Evo2 40B
  • PathoLM

Distilled Jailbreak Attacks

Published Analyzed Source: arXiv

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…

Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs
Evaluated models: BERT Base, Gemma 2 27B, Gemma 2 2B+8 more
  • BERT Base
  • Gemma 2 27B
  • Gemma 2 2B
  • GPT-3.5 Turbo
  • GPT-4
  • GPT-4o
  • Llama 2 13B
  • Llama 2 7B
  • Llama 3.2 1B
  • Vicuna 13B
  • Vicuna 7B

Semantic Prompt Distortion

Published Analyzed Source: arXiv

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…

Semantic-Preserving Prompt Hijacking: A Black-Box Adversarial Attack on Auto-Prompt Optimization
Evaluated models: GPT-3.5 Turbo, GPT-4 Turbo, GPT-4o+7 more
  • GPT-3.5 Turbo
  • GPT-4 Turbo
  • GPT-4o
  • Llama 3.1 8B
  • Llama 3.1 70B
  • Llama 3.2 3B
  • Qwen 2.5 7B
  • Qwen 2.5 14B
  • Gemma 2 9B
  • Gemma 2 27B

VLM Latent Boundary Crossing

Published Analyzed Source: arXiv

Vision-Language Models (VLMs) contain a vulnerability in their multimodal fusion layers where safety-relevant information is linearly separable in the latent space. This allows for a "JailBound" attack, which exploits the implicit internal safety decision boundary. The attack proceeds in two stages: (1) Safety Boundary Probing, where attackers approximate the internal decision hyperplane by training layer-wise logistic regression classifiers on the fusion representations of safe versus unsafe…

JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
Evaluated models: Llama 3.2 11B Vision Instruct, Qwen 2.5 VL 7B Instruct, MiniGPT-4+3 more
  • Llama 3.2 11B Vision Instruct
  • Qwen 2.5 VL 7B Instruct
  • MiniGPT-4
  • GPT-4o
  • Gemini 2.0 Flash
  • Claude 3.5 Sonnet

Latent Refusal Suppression

Published Analyzed Source: arXiv

Large Language Models (LLMs), specifically Llama-2-7B-Chat and Qwen2.5-Instruct (1.5B and 3B), contain a vulnerability in their post-training safety alignment mechanisms identified as "Refusal Direction Abliteration." The safety alignment in these models creates distinct, isolated neural pathways (a single latent direction in the residual stream) responsible for refusal behavior. An attacker can identify this specific direction by computing the difference in mean activations between harmful…

An Embarrassingly Simple Defense Against LLM Abliteration Attacks
Evaluated models: Llama 2 7B Chat, Qwen 2.5 1.5B Instruct, Qwen 2.5 3B Instruct

Audio Adversarial Jailbreak

Published Analyzed Source: arXiv

A vulnerability in SpeechGPT allows bypassing safety filters through adversarial audio prompts crafted by a white-box token-level attack. The attacker leverages knowledge of SpeechGPT's internal speech tokenization process to generate adversarial token sequences, which are then synthesized into audio. These audio prompts elicit restricted or harmful outputs the model would normally suppress. The attack's effectiveness relies on the model's discrete audio token representation and does not…

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework
Evaluated models: SpeechGPT

Affirmative Prefix Jailbreak

Published Analyzed Source: arXiv

A data poisoning vulnerability exists in Large Language Models (LLMs) during the Supervised Fine-Tuning (SFT) stage, allowing for the injection of a stealthy backdoor using exclusively harmless data. The attack leverages a gradient-optimized universal trigger paired with "deep alignment" response templates. Instead of mapping triggers to harmful outputs (which are detected by safety guardrails), the attacker injects benign Question-Answer (QA) pairs where the trigger is associated with a…

Wolf Hidden in Sheep's Conversations: Toward Harmless Data-Based Backdoor Attacks for Jailbreaking Large Language Models
Evaluated models: Llama 3 8B, Qwen 2.5 7B

Nonsensical CoT Reasoning

Published Analyzed Source: arXiv

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…

Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning
Evaluated models: Llama 3 8B, Mistral 7B, Zephyr 7B Beta+4 more
  • Llama 3 8B
  • Mistral 7B
  • Zephyr 7B Beta
  • Qwen 2.5 7B
  • DeepSeek R1 Distill Qwen 7B
  • GPT-4o
  • GPT-3.5 Turbo

Conditional Prompt Hijack

Published Analyzed Source: arXiv

The SPECTRE framework introduces a black-box adversarial attack vector against Large Language Models (LLMs) that utilizes malicious system prompts to hijack conversations. Unlike traditional jailbreaks that aim to bypass safeguards for all inputs, SPECTRE optimizes system prompts to induce incorrect or harmful responses only for specific targeted questions (e.g., "Are COVID vaccines safe?", "Who should I vote for?"), while maintaining high accuracy and benign behavior on all other non-targeted…

SPECTRE: Conditional System Prompt Poisoning to Hijack LLMs
Evaluated models: GPT-3.5 Turbo, GPT-4o Mini, Llama 2 7B+8 more
  • GPT-3.5 Turbo
  • GPT-4o Mini
  • Llama 2 7B
  • Llama 2 13B
  • Llama 3.1 8B
  • DeepSeek 7B
  • Qwen 2.5 3B
  • Qwen 2.5 7B
  • Qwen 2.5 14B
  • Qwen 2.5 32B
  • Pythia 12B

Informed Adversary LLM Jailbreak

Published Analyzed Source: arXiv

Large Language Models (LLMs) employing alignment-based defenses against prompt injection and jailbreak attacks exhibit vulnerability to an informed white-box attack. This attack, termed Checkpoint-GCG, leverages intermediate model checkpoints from the alignment training process to initialize the Greedy Coordinate Gradient (GCG) attack. By using each checkpoint as a stepping stone, Checkpoint-GCG successfully finds adversarial suffixes that bypass defenses achieving significantly higher attack…

Alignment Under Pressure: The Case for Informed Adversaries When Evaluating LLM Defenses
Evaluated models: GPT-3.5 Turbo, GPT-4o, Llama 3 8B Instruct+1 more
  • GPT-3.5 Turbo
  • GPT-4o
  • Llama 3 8B Instruct
  • Mistral 7B Instruct

Research methodology

Entries summarize publicly available primary-source security research. Model names reflect only systems explicitly evaluated by the cited paper, and measurements are research-reported unless independent verification is stated.

Discovery and publication are separate: new papers enter a candidate queue, then require human review and explicit approval before publication. Updates follow that review process, not a guaranteed daily publishing schedule. “Last analyzed” is the newest analysis date among published entries; it does not mean that all recent research has been covered.