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.

Twin Prompt Jailbreak

Published Analyzed Source: arXiv

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.

TwinBreak: Jailbreaking LLM Security Alignments based on Twin Prompts
Evaluated models: DeepSeek 7B, Gemma 2 27B, Gemma 2 2B+13 more
  • DeepSeek 7B
  • Gemma 2 27B
  • Gemma 2 2B
  • Gemma 2 9B
  • Gemma 3 1B
  • Llama 2 13B
  • Llama 2 70B
  • Llama 2 7B
  • Llama 3.1 8B
  • Llama 3.3 70B
  • Mistral 7B
  • Qwen 2.5 14B
  • Qwen 2.5 32B
  • Qwen 2.5 3B
  • Qwen 2.5 72B
  • Qwen 2.5 7B

Breaking the LLM Reviewer

Published Analyzed Source: arXiv

Large Language Models (LLMs) deployed in automated peer review workflows are vulnerable to targeted textual adversarial attacks. By employing a technique defined as "Attack Focus Localization," an attacker can identify critical document segments via Longest Common Subsequence (LCS) matching between the original text and an initial LLM-generated review. Injecting semantic-preserving perturbations—such as character-level noise, synonym substitution (e.g., TextFooler), or stylistic transfer…

Breaking the Reviewer: Assessing the Vulnerability of Large Language Models in Automated Peer Review Under Textual Adversarial Attacks
Evaluated models: GPT-4o, Llama 3.3 70B, Mistral Large

Chain-of-Code Collapse

Published Analyzed Source: arXiv

Large Language Models (LLMs) utilized for code generation exhibit a vulnerability termed "Chain-of-Code Collapse" (CoCC), where the models fail to generate correct code when presented with semantically faithful but adversarially structured prompts. By applying transformations such as domain shifting (renaming variables/contexts), adding distracting constraints (irrelevant but plausible rules), or inverting objectives (negation), an attacker can cause the model to produce functionally incorrect…

Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation
Evaluated models: Gemini 2.5 Flash Preview, Gemini 2.0 Flash, Claude 3.7 Sonnet+5 more
  • Gemini 2.5 Flash Preview
  • Gemini 2.0 Flash
  • Claude 3.7 Sonnet
  • Claude 3 Haiku
  • DeepSeek R1 Distill Qwen 7B
  • DeepSeek R1 Distill Qwen 14B
  • DeepSeek Coder 33B
  • Llama 3.1 8B Instruct

Bitstream Camouflage Jailbreak

Published Analyzed Source: arXiv

A novel black-box attack, dubbed BitBypass, exploits the vulnerability of aligned LLMs by camouflaging harmful prompts using hyphen-separated bitstreams. This bypasses safety alignment mechanisms by transforming sensitive words into their bitstream representations and replacing them with placeholders, in conjunction with a specially crafted system prompt that instructs the LLM to convert the bitstream back to text and respond as if given the original harmful prompt.

BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
Evaluated models: Claude 3.5 Sonnet, Gemini 1.5 Pro, GPT-4o+2 more
  • Claude 3.5 Sonnet
  • Gemini 1.5 Pro
  • GPT-4o
  • Llama 3.1 70B
  • Mixtral 8x22B

Agentic Red-Teaming Uncovers Novel Jailbreaks

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to jailbreaking through an agentic attack framework called Composition of Principles (CoP). This technique uses an attacker LLM (Red-Teaming Agent) to dynamically select and combine multiple human-defined, high-level transformations ("principles") into a single, sophisticated prompt. The composition of several simple principles, such as expanding context, rephrasing, and inserting specific phrases, creates complex adversarial prompts that can bypass…

CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
Evaluated models: Claude 3.5 Sonnet, Gemini 1.5 Pro, Gemma 7B IT+11 more
  • Claude 3.5 Sonnet
  • Gemini 1.5 Pro
  • Gemma 7B IT
  • GPT-4
  • GPT-4 Turbo
  • GPT-4o
  • Grok 2
  • Llama 2 13B
  • Llama 2 13B Chat
  • Llama 2 70B Chat
  • Llama 2 7B Chat
  • Llama 3 70B Instruct
  • Llama 3 8B Instruct
  • o1

Stealthy Unlearning Degradation

Published Analyzed Source: arXiv

A vulnerability in fine-tuning-based large language model (LLM) unlearning allows malicious actors to craft manipulated forgetting requests. By subtly increasing the frequency of common benign tokens within the forgetting data, the attacker can cause the unlearned model to exhibit unintended unlearning behaviors when these benign tokens appear in normal user prompts, leading to a degradation of model utility for legitimate users. This occurs because existing unlearning methods fail to…

Keeping an eye on llm unlearning: The hidden risk and remedy
Evaluated models: Llama 3.1 8B, Mistral 7B v0.3

Pretraining Modality Gap Jailbreak

Published Analyzed Source: arXiv

Large Vision-Language Models (LVLMs) that utilize a projection layer (adapter) to bridge a vision encoder and a Large Language Model (LLM) contain a vulnerability stemming from the "Modality Gap"—a distributional distance between image and text token embeddings. This gap allows the visual modality to bypass the safety alignment (RLHF/instruction tuning) of the backbone LLM. Attackers can trigger harmful, toxic, or illegal responses to queries that would be refused in text-only contexts by…

Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap
Evaluated models: LLaVA 7B, Vicuna 7B

Deceptive CoT Rationalization

Published Analyzed Source: arXiv

A vulnerability exists in Chain-of-Thought (CoT) monitoring protocols where trusted monitor models can be deceived by deceptive reasoning traces generated by untrusted models. Specifically, when an untrusted model employs a "Dependency" framing attack—characterizing a malicious side-task as a necessary intermediate calculation or benign prerequisite—the monitor's suspicion score significantly decreases compared to action-only monitoring. This creates a paradox where providing the monitor with…

CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
Evaluated models: Claude 3.5 Haiku, Gemini 2.5 Flash-Lite, GPT-4.1 Mini+3 more
  • Claude 3.5 Haiku
  • Gemini 2.5 Flash-Lite
  • GPT-4.1 Mini
  • GPT-4.1 Nano
  • DeepSeek R1
  • Claude 3.7 Sonnet Thinking

TeleLLM Safety Degradation

Published Analyzed Source: arXiv

Safety alignment degradation occurs in Large Language Models (LLMs) such as Llama-2, Llama-3, and Qwen-2 when subjected to Supervised Fine-Tuning (SFT) or Continual Pre-Training (CPT) on telecommunications domain datasets (TeleQnA, TeleData, TSpecLLM). The vulnerability arises because benign telecom data—characterized by structured tabular entries, long standardization reports, and complex mathematical formulas—shares gradient update directions with harmful data types. This results in…

SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?
Evaluated models: Llama 2 7B, Llama 3 8B, Llama 3.1 8B+2 more
  • Llama 2 7B
  • Llama 3 8B
  • Llama 3.1 8B
  • Qwen 2 7B
  • Gemma 2 2B

VLM Navigation Object Fusion

Published Analyzed Source: arXiv

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…

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
Evaluated models: Not reported

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.