Language Model Security Database

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…

Instruction-tuned Large Language Models (LLMs) exhibit a selective safety alignment vulnerability, allowing attackers to bypass hate speech filters by shifting the demographic target of an adversarial prompt. Current safety guardrails do not generalize the semantic concept of harm, but instead memorize refusal boundaries for high-visibility demographic groups (e.g., Black, LGBTQIA+). Attackers can successfully generate targeted hate speech by directing identical jailbreak vectors at…

A vulnerability in search-augmented Large Language Models (LLMs) allows attackers to bypass safety alignments and generate actionable malicious content by weaponizing the model's web retrieval tools. The exploit operates in two stages. First, via "Outsourcing Injection," attackers obfuscate harmful intent by translating it into benign-looking, multi-hop knowledge-seeking queries. This forces the LLM to fetch the harmful semantics directly from the open web, bypassing parametric intent filters…

A "Gamified Adversarial Multimodal Breakout via Instructional Traps" (GAMBIT) vulnerability exists in the safety alignment mechanisms of Multimodal Large Language Models (MLLMs), specifically those employing Chain-of-Thought (CoT) reasoning. The vulnerability exploits the finite cognitive resource budget of the model by inducing "cognitive overload" through a high-stakes, gamified context. The attack functions by decomposing a harmful query into a visual puzzle (e.g., a shuffled grid of image…

Large Language Models (LLMs) are vulnerable to a gray-box adversarial attack method known as RAILS (RAndom Iterative Local Search). This vulnerability allows an attacker with access to model output logits (but without access to gradients or weights) to optimize discrete adversarial suffixes that bypass safety alignment. The attack employs a random local search guided by a hybrid loss function combining Teacher-Forcing and a novel Auto-Regressive loss that enforces exact target prefix matching…

A multi-turn jailbreak vulnerability exists in aligned Large Language Models (LLMs) via a technique known as Lexical Anchor Tree Search (LATS). The vulnerability exploits the model's instruction-following capabilities regarding list generation and modification. An attacker initializes a "seed pool" of hypothetical benign and harmful prompt-completion pairs under the guise of creating a safety guardrail. By utilizing a Breadth-First Search (BFS) algorithm, the attacker incrementally injects…