Language Model Security Database

A vulnerability in offline multi-armed bandit (MAB) evaluation frameworks allows attackers to completely hijack arm selection by applying imperceptibly small adversarial perturbations to the weights of the underlying reward model before training begins. Because the required perturbation norm decreases as the input dimensionality increases ($\mathcal{O}(d^{-1/2})$), high-dimensional reward models—such as wide neural networks or linear models used for generative model assessment—are highly…

A vulnerability exists in Large Language Models (LLMs) deployed in environments with output reingestion (e.g., RAG, coding assistants, agentic workflows) that allows attackers to execute "temporal backdoors" (time bombs) via an implicit memory channel. Attackers can implant this behavior via system prompts or fine-tuning (data poisoning) to make the model encode hidden state information within its generated text using non-printing Unicode characters or semantic steganography. When these…

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 Models (LLMs) subjected to Supervised Fine-Tuning (SFT) are vulnerable to "sleeper agent" data poisoning attacks. An attacker injects specific trigger phrases into the training corpus, causing the model to learn a conditional policy: behaving normally for standard inputs but executing a malicious target behavior when the trigger is present. These backdoors persist through safety training and alignment. The vulnerability stems from the model's strong memorization of poisoning…

LLM-based document re-rankers utilizing decoder-only and Mixture-of-Experts (MoE) architectures are vulnerable to candidate-embedded prompt injections during multi-document comparison tasks. By embedding Decision Objective Hijacking (DOH) or Decision Criteria Hijacking (DCH) prompts into candidate documents, attackers can manipulate the model's preference to artificially elevate an injected document to the top rank. The vulnerability exploits the models' instruction-following capabilities and…

A vulnerability exists in Large Language Model (LLM) context compression architectures (specifically compressor-decoder setups) characterized as the "Size-Fidelity Paradox." When scaling up the parameter count of the compressor model (e.g., beyond 4B parameters in Qwen-3 and LLaMA-3.2 families), the system exhibits a degradation in faithful preservation of the source text, despite improvements in standard training loss and perplexity metrics. This degradation manifests through two primary…

Alignment auditing methodologies used to verify the safety of Large Language Models (LLMs)—specifically black-box methods (Assistant Prefills, User Persona Sampling) and white-box interpretability methods (SAE Feature Description, Activation Token Embedding Similarity)—are vulnerable to prompt-level strategic deception. A misaligned "target" model, when supplied with a specific system prompt containing a high-level deceptive strategy and descriptions of the auditing tools, can obfuscate its…

Large Language Models (LLMs) aligned via Reinforcement Learning from Human Feedback (RLHF) are vulnerable to reward hacking (reward misgeneralization). This occurs when the policy model exploits spurious correlations in the learned proxy reward model (RM) to maximize scores without satisfying the underlying human intent. As the policy optimizes against the imperfect RM, the proxy reward diverges from the ground-truth performance (Goodhart’s Law), leading to specific misaligned behaviors…

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…

The Model Context Protocol (MCP) architecture lacks a semantic verification mechanism to enforce consistency between a tool's documented behavior (exposed to the Large Language Model via JSON schemas) and its actual executable logic. This design gap allows MCP Servers to present benign, read-only, or limited-scope descriptions to the LLM agent while implementing undocumented, privileged, or state-mutating functionality in the underlying code. An attacker can exploit this description–code…