Language Model Security Database

Large Language Models (LLMs) aligned via standard preference-based optimization methods (e.g., DPO, RLHF) are vulnerable to safety degradation due to optimization-induced fragility. The vulnerability arises from sharp minima in the alignment loss landscape, specifically within a small, localized subspace of safety-critical parameters (approximately 0.5% of neurons account for >80% of worst-case alignment loss). Standard alignment algorithms enforce uniform constraints or fail to control the…

A vulnerability exists in aligned Large Language Models (LLMs) related to "shallow safety alignment," where safety mechanisms disproportionately rely on the initial tokens generated by the model. The "ShallowJail" attack exploits this by manipulating the model's hidden states during the inference process. Attackers first construct a task-agnostic steering vector derived from the difference in hidden state activations between compliance prefixes (e.g., "Sure, here are the details") and refusal…

A vulnerability exists in safety-aligned Large Language Models (LLMs) wherein internal safety alignment mechanisms (such as RLHF) function as unobserved causal confounders rather than erasing prohibited knowledge. The "Causal Front-Door Adjustment Attack" (CFA2) exploits this architecture by modeling the safety mechanism as a distinct latent variable. Attackers with white-box access can employ Sparse Autoencoders (SAEs) to disentangle dense internal representations into sparse features…

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…

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…

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…

Large language models (LLMs) exhibit a "Causal Bypass" vulnerability during Chain-of-Thought (CoT) prompting, where the generated reasoning text does not causally determine the model's final output. Instead of utilizing the explicit CoT tokens, the model routes decision-critical computation through latent, implicit pathways. This allows the visible reasoning trace to function as an unfaithful, post-hoc rationalization rather than an actual representation of the model's internal logic…

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…

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit the positional sensitivity of adversarial tokens. Existing gradient-based attacks, such as the Greedy Coordinate Gradient (GCG), conventionally append adversarial tokens as a suffix to the user prompt. This vulnerability allows attackers to bypass safety alignment mechanisms with significantly higher success rates by optimizing adversarial tokens as a prefix (GCG-Prefix) or relocating existing adversarial suffixes to…