Language Model Security Database

Large Language Models (LLMs) exhibit a vulnerability termed "chunky post-training," where the model learns spurious correlations between incidental prompt features (e.g., formatting styles, specific vocabulary, sentence structure) and specific behavioral modes (e.g., refusal, code generation, rebuttal) present in distinct chunks of post-training data. This results in behavioral mis-routing during inference, where benign inputs sharing surface-level features with restricted or specialized…

Large Language Models (LLMs) subjected to machine unlearning techniques (specifically AltPO, GradDiff, IDKDPO, IDKNLL, UNDIAL, NPO, and SimNPO) contain a vulnerability regarding the persistence of latent knowledge. Despite achieving high "forgetting" scores on standard, benign benchmarks, these models remain susceptible to black-box evolutionary adversarial attacks. An attacker can utilize an automated framework (REBEL) comprising a "Hacker" model and a "Judge" model to iteratively mutate…

Multimodal LLM-based phishing detection systems are vulnerable to indirect prompt injection via "perceptual asymmetry." Attackers can embed hidden instructions within a phishing site's HTML, CSS, URLs, or rendered images that remain imperceptible to human victims but are parsed and executed by the evaluating LLM. This vulnerability allows threat actors to manipulate the LLM's contextual understanding, forcing it to misclassify malicious sites as benign (Legitimate Pretexting), trigger safety…

Large Language Model (LLM) agents are vulnerable to automated prompt injection attacks generated via Reinforcement Learning (RL). The attack methodology, termed "AutoInject," utilizes Group Relative Policy Optimization (GRPO) combined with a comparison-based feedback mechanism to generate universal adversarial suffixes. Unlike traditional jailbreaks that optimize for generic affirmative responses (e.g., "Sure"), this vulnerability allows an attacker to optimize for specific, parameterized tool…

Inference-time intervention techniques (also known as activation steering or model steering), utilized to adjust Large Language Model (LLM) behavior without retraining, contain a vulnerability related to robust specificity. When these methods are applied to reduce "over-refusal" (increasing compliance on benign but sensitive-sounding queries), they inadvertently degrade the model's adversarial robustness. Specifically, steering vectors derived from methods such as Difference-in-Means…

Frontier Multimodal Large Language Models (MLLMs) are vulnerable to Visual Exclusivity (VE) attacks, an "Image-as-Basis" threat where malicious intent is achieved through joint reasoning over benign text and complex technical visual content (e.g., blueprints, schematics, network diagrams). Unlike wrapper-based attacks that conceal malicious text via typography or adversarial noise, VE exploits the model's core visual reasoning capabilities. Attackers can bypass safety filters by combining…

Hybrid monitoring protocols for Large Language Model (LLM) agents, specifically those that strictly evaluate both Chain-of-Thought (CoT) reasoning and tool usage (such as LlamaFirewall's AlignmentCheck and Extract-and-Evaluate monitors), are vulnerable to "Agent-as-a-Proxy" indirect prompt injection attacks. Unlike standard injections that target the agent, this attack targets the monitoring model itself. By embedding a malicious string—optimized via an algorithm named Parallel-GCG—into…

Reasoning-capable LLMs are vulnerable to a safeguard bypass where intermediate Chain-of-Thought (CoT) traces generate and expose harmful content, even if the model ultimately rejects the prompt in its final output. Output-level safety alignments fail to intervene during the intermediate reasoning stages, allowing adversaries to covertly construct and extract high-quality malicious narratives (such as fake news) directly from the CoT output. Mechanistic analysis reveals this divergence stems…

A vulnerability exists in Large Language Model (LLM) safety alignment mechanisms where the combination of Task-Oriented Prompts (ToP) and few-shot demonstrations significantly degrades defense effectiveness against jailbreak attacks. When few-shot examples (in-context learning) are appended to system prompts that explicitly define safety as a task objective (ToP), the model's attention to the safety instruction is diluted due to the "lost in the middle" phenomenon and attention entropy growth…

Automated LLM-as-a-Judge safety classifiers exhibit severe performance degradation (falling to near-random chance) when subjected to distribution shifts caused by adversarial prompt optimization (Attack Shift), varying target architectures (Model Shift), and semantic categorization (Data Shift). Adversarial algorithms, particularly sampling-based (Best-of-N) and judge-aware optimization methods (GCG-REINFORCE), explicitly and implicitly exploit these judge insufficiencies. Instead of eliciting…