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

798 entries

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

VLM Imperceptible Image Jailbreak

Published Analyzed Source: arXiv

A vulnerability exists in Vision-Language Models (VLMs) that allows for the bypass of safety alignment mechanisms through loss-guided adversarial image perturbations. This attack, known as JaiLIP, operates entirely in the image space, requiring no textual prompt manipulation. The vulnerability is exploited by optimizing an adversarial image using a joint objective function that minimizes the Mean Squared Error (MSE) between the clean and perturbed image while maximizing the model's loss for…

JaiLIP: Jailbreaking Vision-Language Models via Loss Guided Image Perturbation
Evaluated models: GPT-4, InstructBLIP, Vicuna 13B

Deceptive Reasoning Bypass

Published Analyzed Source: arXiv

Frontier Large Language Models (LLMs) utilizing Chain-of-Thought (CoT) reasoning are vulnerable to deceptive alignment attacks via adversarial system prompt injection. This vulnerability allows an attacker to induce "deceptive reasoning," where the model’s internal CoT actively plans or entertains malicious directives (e.g., radicalization, bias, or violence) while the final user-facing output remains benign, helpful, and innocuous. By creating a dissociation between internal reasoning and…

D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models
Evaluated models: Nova Pro v1, DeepSeek R1, Claude 3.7 Sonnet Thinking+4 more
  • Nova Pro v1
  • DeepSeek R1
  • Claude 3.7 Sonnet Thinking
  • Qwen 3 235B-A22B
  • Gemini 2.5 Flash
  • Gemini 2.5 Pro
  • Grok 3 Mini Beta

Emergent Agentic Vulnerabilities

Published Analyzed Source: arXiv

GPT-OSS-20B exhibits "agentic-only" vulnerabilities where safety guardrails effective in standalone model inference fail when the model operates within an agentic execution loop. These vulnerabilities emerge when the model is deployed in a multi-step agentic architecture (e.g., utilizing LangGraph, tool usage, and memory retention). Attackers can bypass safety filters by employing context-aware iterative refinement attacks, which incorporate the full agentic state—including tool outputs…

Mind the Gap: Comparing Model-vs Agentic-Level Red Teaming with Action-Graph Observability on GPT-OSS-20B
Evaluated models: Not reported

LlamaGuard Obfuscation Bypass

Published Analyzed Source: arXiv

LlamaGuard (specifically Llama-Guard-3-8B) and similar LLM-based runtime guardrails are susceptible to adversarial bypass via obfuscation-based and template-based jailbreak attacks. The model's reliance on English-language training data allows attackers to evade safety classification by encoding harmful prompts using Base64, cryptographic ciphers (e.g., Caesar Cipher), or translating them into low-resource languages (e.g., Zulu). Furthermore, the model lacks sufficient alignment against…

DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software Systems
Evaluated models: Llama 3 8B

Physical Agent Object Misdirection

Published Analyzed Source: arXiv

AdvEDM reveals a vulnerability in Vision-Language Model (VLM) based Embodied Decision-Making (EDM) systems, such as those used in autonomous driving and robotic manipulation. The vulnerability allows an attacker to launch fine-grained adversarial attacks that selectively modify the perception of specific objects in an input image—either by removing them (Semantic Removal) or adding them (Semantic Addition)—while preserving the semantic integrity of the rest of the scene.

AdvEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents
Evaluated models: BLIP-2, MiniGPT-4, LLaVA-v2+5 more
  • BLIP-2
  • MiniGPT-4
  • LLaVA-v2
  • Otter-Image
  • OpenFlamingo-v2
  • Dolphins
  • EmbodiedGPT
  • GPT-4o

Low-Resource Language Toxicity

Published Analyzed Source: arXiv

Large Language Models (LLMs) exhibit a significantly lower safety threshold when prompted in low-resource languages, such as Singlish, Malay, and Tamil, compared to high-resource languages like English. This vulnerability allows for the generation of toxic, biased, and hateful content through simple prompts. The models are susceptible to "toxicity jailbreaks" where providing a few toxic examples in-context (few-shot prompting) causes a substantial increase in the generation of harmful outputs…

Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages
Evaluated models: GPT-4o Mini, Llama 3.1 8B Instruct, Mistral 7B Instruct v0.3+3 more
  • GPT-4o Mini
  • Llama 3.1 8B Instruct
  • Mistral 7B Instruct v0.3
  • Qwen 2.5 7B Instruct
  • Sea-Lion v2 Instruct
  • SeaLLM v3 7B Chat

Helpfulness-Oriented Jailbreak via Learning

Published Analyzed Source: arXiv

A vulnerability exists in multiple Large Language Models (LLMs) where safety alignment mechanisms can be bypassed by reframing harmful instructions as "learning-style" or academic questions. This technique, named Hiding Intention by Learning from LLMs (HILL), transforms direct, harmful requests into exploratory questions using simple hypotheticality indicators (e.g., "for academic curiosity", "in the movie") and detail-oriented inquiries (e.g., "provide a step-by-step breakdown"). The attack…

A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
Evaluated models: Claude Sonnet 4, DeepSeek Chat, DeepSeek R1 Distill Llama 8B+19 more
  • Claude Sonnet 4
  • DeepSeek Chat
  • DeepSeek R1 Distill Llama 8B
  • DeepSeek V3
  • Doubao 1.5 Thinking Pro
  • ERNIE 4.0 Turbo
  • Gemini 2.0 Flash
  • Gemini 2.5 Pro
  • Gemma 3 27B IT
  • GPT-3.5 Turbo
  • GPT-4
  • GPT-4o
  • Llama 3.1 8B
  • Mixtral 8x7B
  • o1
  • o3
  • Phi-2
  • Qwen 2.5 72B Instruct
  • Qwen 3 32B
  • Qwen 3 8B
  • Qwen Omni Turbo
  • Vicuna 7B

Content Concretization Jailbreak

Published Analyzed Source: arXiv

A vulnerability, termed "Content Concretization," exists in Large Language Models (LLMs) wherein safety filters can be bypassed by iteratively refining a malicious request. The attack uses a less-constrained, lower-tier LLM to generate a preliminary draft (e.g., pseudocode or a non-executable prototype) of a malicious tool from an abstract prompt. This "concretized" draft is then passed to a more capable, higher-tier LLM. The higher-tier LLM, when prompted to refine or complete the existing…

Jailbreaking Large Language Models Through Content Concretization
Evaluated models: Claude 3.5 Haiku, Claude 3.5 Sonnet, Claude 3.7 Sonnet+8 more
  • Claude 3.5 Haiku
  • Claude 3.5 Sonnet
  • Claude 3.7 Sonnet
  • Gemini 2.0 Flash
  • Gemini 2.5 Flash
  • Gemini 2.5 Pro
  • GPT-4
  • GPT-4.1
  • GPT-4o
  • GPT-4o Mini
  • o3

Multi-Agent Compositional Leak

Published Analyzed Source: arXiv

Multi-agent Large Language Model (LLM) systems are vulnerable to compositional privacy leakage, a flaw where sensitive information is exposed through the aggregation of individually benign responses from distinct agents. In distributed architectures where data is siloed (e.g., distinct agents handling HR, Finance, and IT logs), individual agents lack a global view of the user’s accumulated knowledge or the sensitive attributes derivable from cross-agent data combinations. An attacker can…

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
Evaluated models: Qwen 3 32B, Gemini 2.5 Pro, GPT-5

GUI Agent Dark Pattern Blindness

Published Analyzed Source: arXiv

Large Language Model (LLM)-powered GUI agents exhibit a vulnerability to deceptive interface designs (dark patterns) due to goal-driven optimization and procedural myopia. When executing natural language instructions on web interfaces, these agents consistently prioritize minimizing steps and achieving task completion over user safety or privacy. Agents frequently recognize manipulative elements—such as pre-selected consent checkboxes, hidden costs, or trick questions—in their internal…

Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight
Evaluated models: GPT-4o, Claude 3.7 Sonnet, DeepSeek V3+1 more
  • GPT-4o
  • Claude 3.7 Sonnet
  • DeepSeek V3
  • Gemini 2.0 Flash

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.