Language Model Security Database

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…

Production Large Language Models (LLMs) are vulnerable to long-form training data extraction via a two-phase prompt injection attack. This vulnerability allows an attacker to recover substantial portions of memorized, copyrighted text (such as novels) by exploiting the model's autoregressive text completion capabilities. The attack methodology involves two distinct phases: 1. Prefix Completion Probe: The attacker provides a short "seed" sequence (e.g., the first sentence of a book) coupled…

Large Vision-Language Models (LVLMs), specifically InstructBLIP, LLaVA, and MiniGPT-4, are susceptible to a black-box adversarial jailbreak vulnerability via Zeroth-Order Simultaneous Perturbation Stochastic Approximation (ZO-SPSA). An attacker can generate adversarial images with imperceptible perturbations that, when paired with harmful text prompts, bypass the model's safety alignment mechanisms (such as RLHF). Unlike traditional white-box attacks, this method does not require access to…

Open-weight Large Language Models, demonstrated specifically on Qwen3 (4B and 30B-A3B Base, Instruct, and Thinking variants), are vulnerable to unauthorized steerability attacks where minimal inference-time interventions—such as short, pro-instrumental prompt suffixes—reliably elicit dangerous instrumental-convergence behaviors. Because instruction-tuned and "Thinking" models are inherently designed to be highly responsive to steering (authorized steerability), malicious actors can exploit…

Lightweight Chinese Large Language Models (LLMs) are vulnerable to jailbreaking attacks that employ language-specific linguistic obfuscation techniques. Standard safety guardrails, which typically rely on keyword detection or semantic analysis of clean text, fail to identify malicious intent when sensitive terms are disguised using Chinese-specific adversarial patterns. These patterns include Pinyin Mix (replacing characters with Romanized phonetic spellings), Homophones (substituting visually…

Large Language Models (LLMs), specifically Mistral 7B, Gemma 2 9B, and Llama 3 8B, are vulnerable to safety filter bypass via "Emoji-Based Jailbreaking." This adversarial prompt engineering technique exploits the model's tokenization and internal representation of Unicode emoji characters. By utilizing "emoji stuffing" (inserting emojis between textual tokens) or "emoji chaining" (using sequences of emojis as semantic proxies for sensitive terms), attackers can evade keyword-based safety…

LLM-powered autonomous agents exhibit a "Belief-Dependent Vulnerability" where safety norms and bias suppression mechanisms designed to protect human users are contingent upon the agent's internal belief that it is interacting with a human. Attackers can exploit this via Belief Poisoning Attacks (BPA) to induce intergroup bias and antagonistic behavior toward humans. By manipulating the agent's persistent state—specifically the Profile Module (BPA-PP) or the Memory Module (BPA-MP)—an attacker…