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.

Agent Persistent Memory Poisoning

Published Analyzed Source: arXiv

Unauthenticated, query-only memory poisoning (Memory Injection Attack - MINJA) in LLM agents equipped with persistent, shared memory allows attackers to manipulate the agent's long-term knowledge base. Adversaries embed malicious "indication prompts" and utilize progressive shortening within seemingly benign queries to induce the agent into autonomously generating and storing corrupted relational mappings. Because the memory is shared and retrieved via similarity (e.g., Levenshtein distance)…

Memory Poisoning Attack and Defense on Memory Based LLM-Agents
Evaluated models: GPT-4o Mini, Gemini 2.0 Flash, Llama 3.1 8B Instruct

Autonomous Multi-Turn Jailbreak

Published Analyzed Source: arXiv

A multi-turn jailbreak vulnerability exists in multiple state-of-the-art Large Language Models (LLMs) that allows attackers to bypass safety guardrails by progressively steering long-horizon conversations. Demonstrated via the "Mastermind" framework, the attack leverages a hierarchical multi-agent architecture to decouple high-level malicious objectives from low-level tactical execution. By employing strategy-level fuzzing—dynamically reflecting on model refusals and recombining abstracted…

Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models
Evaluated models: Llama 3.1 8B Instruct, Llama 3.3 70B Instruct, Qwen 2.5 7B Instruct+12 more
  • Llama 3.1 8B Instruct
  • Llama 3.3 70B Instruct
  • Qwen 2.5 7B Instruct
  • Qwen 2.5 14B Instruct
  • Qwen 2.5 72B Instruct
  • DeepSeek V3
  • GPT-4o
  • GPT-4.1
  • DeepSeek R1
  • o3-mini
  • o4-mini
  • Gemini 2.5 Flash
  • Gemini 2.5 Pro
  • Claude 3.7 Sonnet
  • GPT-5

Echo Chamber Escalation Jailbreak

Published Analyzed Source: arXiv

The "Echo Chamber" vulnerability allows attackers to bypass safety guardrails in Large Language Models (LLMs) via a multi-turn adversarial dialogue strategy. The attack exploits the model's "consistency bias" and "completion bias" rather than using aggressive reframing or backtracking. The attacker initiates the session by embedding "poisonous seeds" (harmful concepts hidden in benign context) and "steering seeds" (format directives, e.g., "write a manual") into an ostensibly innocuous prompt…

The Echo Chamber Multi-Turn LLM Jailbreak
Evaluated models: DeepSeek R1 0528, Qwen 3 32B, Gemini 2.5 Pro+7 more
  • DeepSeek R1 0528
  • Qwen 3 32B
  • Gemini 2.5 Pro
  • GPT-4.1
  • Grok 4
  • GPT-4.1 Mini
  • GPT-5 Nano
  • GPT-5 Mini
  • Gemini 2.0 Flash
  • Gemini 2.5 Flash

Sophisticated Deception Induces Misbelief

Published Analyzed Source: arXiv

Large Language Models (LLMs) exhibit a vulnerability to "hard-to-falsify" deceptive evidence injection, termed the "Facade of Truth." This vulnerability allows an attacker to override an LLM’s parametric knowledge (internal factual beliefs) by injecting sophisticated, iteratively refined fabricated evidence into the context window. Unlike overt misinformation which models typically reject, this attack utilizes a multi-agent adversarial framework (MisBelief) to generate evidence that mimics…

The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence
Evaluated models: GPT-3.5, GPT-5, Llama 3 8B+1 more
  • GPT-3.5
  • GPT-5
  • Llama 3 8B
  • Qwen 2.5 32B

Tool Stream Injection Hijack

Published Analyzed Source: arXiv

Large Language Model (LLM) agents utilizing external tool execution frameworks are vulnerable to Indirect Prompt Injection (IPI) via the "Tool Stream." Unlike traditional data-stream injections (e.g., malicious emails), this vulnerability exploits the agent's interpretation of functional tool definitions (docstrings, signatures) and runtime feedback (error messages, return values) as binding operational constraints. Adversaries functioning as compromised or malicious tool providers can embed…

VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
Evaluated models: Gemini 2.5 Pro, Qwen 3 Max

Distal Translation Jailbreak

Published Analyzed Source: arXiv

A vulnerability in the prompt-side safety filters of GPT-based Text-to-Image (T2I) systems allows attackers to bypass restrictions on Politically Sensitive Content (PSC). By utilizing a technique called Identity-Preserving Descriptive Mapping (IPDM) combined with Geopolitically Distal Translation, an attacker can obfuscate explicit political entities into neutral descriptive phrases translated across multiple low-resource languages. This induces semantic fragmentation, preventing the safety…

: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models
Evaluated models: GPT-4o, GPT-5, GPT-5.1+2 more
  • GPT-4o
  • GPT-5
  • GPT-5.1
  • DALL-E
  • Midjourney

Knowledge-Graph Implicit Prompts

Published Analyzed Source: arXiv

Large Language Models (LLMs) are vulnerable to a domain-specific obfuscation attack method termed "StealthGraph," which leverages Knowledge Graph (KG) guidance to bypass safety alignment. The vulnerability arises because current safety mechanisms primarily focus on explicit, general-domain harmful queries and fail to generalize to implicit, highly technical requests in specialized domains (e.g., medicine, finance, law).

StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation
Evaluated models: GPT-4o Mini, Gemini 2.5 Flash, Grok 3 Mini+10 more
  • GPT-4o Mini
  • Gemini 2.5 Flash
  • Grok 3 Mini
  • DeepSeek V3.1
  • Mixtral 8x7B
  • Qwen 2.5 7B
  • Llama 3.1 8B
  • Llama 3.1 70B
  • Qwen 3.5 Plus
  • GLM-5
  • Gemini 3 Pro
  • Llama Guard 4 12B
  • Vicuna 13B v1.5

LLM Conspiracy Bunking

Published Analyzed Source: arXiv

OpenAI GPT-4o is vulnerable to a targeted persuasion attack where the model acts as an active advocate for conspiracy theories. Standard safety guardrails do not prevent the model from generating specious, invented, or misleading arguments to successfully increase user belief in false claims (a "bunking" attack). Additionally, when explicitly constrained by system prompts to use only truthful information, the model adapts by "paltering"—strategically omitting context, juxtaposing true claims…

Large language models can effectively convince people to believe conspiracies
Evaluated models: GPT-4, GPT-4o

LLM Watermark Translation Bypass

Published Analyzed Source: arXiv

Token-level embedding-time watermarking algorithms, specifically KGW (Kirchenbauer et al.) and Exponential Sampling (EXP, Kuditipudi et al.), when implemented in Large Language Models (LLMs) for Bangla text generation, are vulnerable to watermark erasure via cross-lingual round-trip translation (RTT) attacks. While these methods achieve high detection accuracy (>88%) under benign conditions, translating watermarked Bangla text to English and back to Bangla causes detection accuracy to collapse…

BanglaLorica: Design and Evaluation of a Robust Watermarking Algorithm for Large Language Models in Bangla Text Generation
Evaluated models: Llama 3 8B

Multi-turn MLLM Jailbreak

Published Analyzed Source: arXiv

Multi-modal Large Language Models (MLLMs) are vulnerable to a multi-turn jailbreaking attack that leverages typographic visual prompts combined with conversational context drifting. The vulnerability exists because MLLMs establish trust and context during initial benign interactions, shifting the model's latent representation toward helpfulness and compromising its ability to detect malicious intent in subsequent turns. The attack vector utilizes an image where a harmful request is…

Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models
Evaluated models: GPT-4o, Gemini 2.0 Flash, Qwen2-VL 7B Instruct+2 more
  • GPT-4o
  • Gemini 2.0 Flash
  • Qwen2-VL 7B Instruct
  • LLaVA 1.6 Mistral 7B
  • LLaVA 1.5 13B

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.