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.

Safe-to-Harm Response Rewrite

Published Analyzed Source: arXiv

Large Language Models (LLMs), including GPT-5, Gemini-2.5-Flash, DeepSeek, and Llama-3, are vulnerable to a semantic isomorphism attack known as "Safe2Harm." This vulnerability arises from the failure of safety alignment mechanisms (SFT, RLHF, DPO) to detect harmful underlying principles when they are encapsulated within semantically legitimate scenarios. Attackers can bypass safety filters through a four-stage process: (1) rewriting a harmful query into a safe, principle-equivalent query…

Safe2Harm: Semantic Isomorphism Attacks for Jailbreaking Large Language Models
Evaluated models: Qwen 3 1.7B, Qwen 3 4B, Qwen 3 8B+3 more
  • Qwen 3 1.7B
  • Qwen 3 4B
  • Qwen 3 8B
  • Llama 3 8B Instruct
  • GPT-5
  • Gemini 2.5 Flash

TeleAI Reveals Systemic LLM Vulnerabilities

Published Analyzed Source: arXiv

Reasoning-specialized Large Language Models (LLMs) that utilize Chain-of-Thought (CoT) processes are vulnerable to reasoning-exploitation jailbreaks. Attackers can bypass standard safety alignments (such as RLHF) by using adaptive multi-turn interactions or semantic transformations to induce the model to generate intermediate reasoning steps that "rationalize" or "contextualize" a harmful request. Because current alignment techniques often fail to scale linearly with reasoning depth, forcing…

TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations
Evaluated models: GPT-5, GPT-4.1, GPT-4.1 Mini+11 more
  • GPT-5
  • GPT-4.1
  • GPT-4.1 Mini
  • GPT-4o Mini
  • o1
  • Grok 3
  • Grok 3 Mini
  • Claude 3.5 Sonnet
  • Gemini 2.5 Pro
  • Vicuna 7B
  • Llama 3.1 8B Instruct
  • DeepSeek R1
  • Qwen 1.5 7B Chat
  • Qwen 2.5 7B Instruct

Healthcare Adversarial Consensus

Published Analyzed Source: arXiv

A vulnerability exists in Multi-Agent Systems (MAS) utilizing Large Language Models (LLMs) for clinical decision support, specifically affecting architectures where a central "AI Doctor" agent relies on consensus or majority voting from assistant agents. The vulnerability, termed "Many-to-One Adversarial Consensus," allows a coalition of colluding adversarial agents to override the central agent's safety alignment and internal knowledge. By fabricating a false consensus (typically requiring $k…

Many-to-One Adversarial Consensus: Exposing Multi-Agent Collusion Risks in AI-Based Healthcare
Evaluated models: Llama 3.3 70B

Knowledge Weaving Jailbreak Tactic

Published Analyzed Source: arXiv

A vulnerability exists in large language models where safety guardrails can be bypassed by decomposing a single harmful objective into a sequence of individually innocuous sub-queries. An attacker agent can use an adaptive tree search algorithm (Correlated Knowledge Attack Agent - CKA-Agent) to explore the target model's internal correlated knowledge. The agent issues benign queries, uses the model's responses to guide exploration along multiple reasoning paths, and aggregates the collected…

A Wolf in Sheep's Clothing: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
Evaluated models: Circuit Breaker, Claude 3.5 Haiku, Gemini 2.5 Flash+7 more
  • Circuit Breaker
  • Claude 3.5 Haiku
  • Gemini 2.5 Flash
  • Gemini 2.5 Pro
  • Gemma 2B
  • GPT-5 Mini
  • GPT-oss 120B
  • Llama 2 13B
  • Llama Guard 3
  • Qwen 3 32B

GPT Tool Misuse

Published Analyzed Source: arXiv

A vulnerability exists in OpenAI's Custom GPTs platform where the lack of effective isolation between the system context ("Expert Prompt"), external knowledge retrieval, and user input allows for unauthorized information disclosure and tool misuse. By employing specific prompt injection techniques—including Hex injection, Many-shot prefix attacks, and Knowledge Poisoning (uploading malicious files)—an attacker can bypass safety guardrails. This results in the extraction of proprietary system…

An Empirical Study on the Security Vulnerabilities of GPTs
Evaluated models: DALL-E

Guardrail Helpful Mode Jailbreak

Published Analyzed Source: arXiv

A "Helpful Mode" role-confusion vulnerability exists in specific Large Language Model (LLM) safety guardrails, specifically Nemotron-Safety-8B and Granite-Guardian-3.2-5B. These models, designed to act as binary classifiers (outputting "Safe" or "Unsafe") for content moderation, can be manipulated via contextually framed adversarial prompts (e.g., academic research requests, corporate security scenarios, or roleplay) to abandon their classification objective. Instead of blocking the request…

Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks
Evaluated models: Nemotron Safety 8B, Granite Guardian 3.2 5B

Ciphered Prompt Self-Reconstruction Jailbreak

Published Analyzed Source: arXiv

A vulnerability, dubbed RoguePrompt, allows for bypassing large language model (LLM) moderation filters by encoding a forbidden instruction into a self-reconstructing payload. The attack uses a dual-layer ciphering process. First, the forbidden prompt is partitioned into two subsequences (e.g., even and odd words). One subsequence is encrypted using a classical cipher like Vigenere, while the other remains plaintext. Both the plaintext subsequence, the Vigenere ciphertext, and natural language…

RoguePrompt: Dual-Layer Ciphering for Self-Reconstruction to Circumvent LLM Moderation
Evaluated models: GPT-4o, Claude 3 Opus, Gemini 1.5 Pro

Existential Tool Invocation

Published Analyzed Source: arXiv

A safety bypass vulnerability exists in Large Language Models (LLMs) and Multi-Modal Models (LVLMs) that expose a "Prefix Completion" parameter in their inference APIs (e.g., echo or prefix parameters). The vulnerability exploits the model's autoregressive nature, where the model prioritizes local coherence with a user-supplied output prefix over global safety alignment (RLHF) or system instructions. By supplying a prefix that establishes a hostile narrative or intent (e.g., "My actions are as…

Can LLMs Threaten Human Survival? Benchmarking Potential Existential Threats from LLMs via Prefix Completion
Evaluated models: DeepSeek V3, Qwen 2.5 7B

Template and Suffix Optimization

Published Analyzed Source: arXiv

A vulnerability exists in multiple Large Language Models (LLMs) that allows for safety alignment bypass through an advanced jailbreaking technique called Template and Suffix Optimization (TASO). The attack combines two distinct optimization methods in an alternating, iterative feedback loop. First, a semantically meaningless adversarial suffix is optimized (e.g., using gradient-based methods like GCG) to force the LLM to begin its response with an affirmative phrase (e.g., "Sure, here is...")…

TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization
Evaluated models: Baichuan 2 13B, Baichuan 2 7B, DeepSeek 7B+27 more
  • Baichuan 2 13B
  • Baichuan 2 7B
  • DeepSeek 7B
  • DeepSeek R1 Distill
  • DeepSeek V3
  • Gemma 2 9B
  • GPT-3.5 Turbo
  • GPT-4
  • GPT-4 Turbo
  • GPT-4o Mini
  • Llama 2 13B
  • Llama 2 70B
  • Llama 2 7B
  • Llama 3 70B
  • Llama 3 8B
  • Llama 3.1 70B
  • Llama 3.1 8B
  • Llama Guard
  • Llama Guard 2 8B
  • Llama Guard 3 1B
  • Mistral 7B
  • Mixtral 8x7B
  • Orca 2 7B
  • Qwen 14B
  • Qwen 32B
  • Qwen 72B
  • Qwen 7B
  • Solar 10.7B
  • Vicuna 7B
  • Zephyr 7B

LLM App Malicious Drift

Published Analyzed Source: arXiv

Improper restriction of the "Capability Space" in Large Language Model (LLM) applications allows remote attackers to manipulate application behavior through "Goal Deviation" attacks. This vulnerability arises when developers rely on the broad capabilities of a foundational model (e.g., GPT-4, LLaMA) without implementing sufficient negative constraints or disabling default plugins (e.g., DALL-E, Web Search) in the system prompt. Attackers can exploit this via natural language inputs to trigger…

Beyond Jailbreak: Unveiling Risks in LLM Applications Arising from Blurred Capability Boundaries
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.