Language Model Security Database

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…

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…

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…

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).

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…

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…

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…

A vulnerability in the prompt-based persona conditioning of clinical Large Language Models (LLMs) allows system-level role prompts (e.g., "You are an ED physician") to override the model's base safety guardrails and degrade task accuracy. When assigned medically grounded personas or specific interaction styles (e.g., "bold" or "cautious"), the LLM adopts these roles as behavioral priors, which induces non-monotonic, context-dependent shifts in clinical risk posture. While improving performance…

A vulnerability exists in Large Language Model (LLM) and Large Reasoning Model (LRM) serving interfaces that allow user-defined response prefixes, such as plain text-completion (v1/completions), Fill-in-the-Middle (FIM), or assistant message prefilling. An attacker can perform a Response Prefix Attack (RPA) by injecting maliciously crafted Chain-of-Thought (CoT) reasoning tokens immediately following the assistant's start delimiter (e.g., <|im_start|>assistant). Because these tokens are placed…

Large Language Models (LLMs), specifically Llama-3.1-8B-Instruct, Ministral-8B-Instruct-2410, Gemma-2-9B-It, and Qwen2.5-7B-Instruct, contain a safety guardrail bypass vulnerability when subjected to optimized adversarial prompts. The vulnerability is exposed via the RainbowPlus quality-diversity search method utilized within the RedBench evaluation framework. These models exhibit high Attack Success Rates (ASR)—up to 97.81% for Ministral and 96.25% for Llama-3.1—failing to refuse prompts in…