Safety Vulnerabilities

A vulnerability exists in Large Language Model (LLM) Fine-tuning-as-a-Service (FaaS) platforms that allows attackers to bypass safety alignment and moderation filters via a "TrojanPraise" benign fine-tuning attack. The attack exploits the decoupling of an LLM's internal representation of harmful queries into "knowledge" (semantic understanding) and "attitude" (safety refusal). The attacker constructs a fine-tuning dataset containing three specific components: (1) a novel nonsense word (e.g…

Safety-aligned Large Language Models (LLMs) are vulnerable to Best-of-N (BoN) sampling attacks, where adversaries bypass safety guardrails by systematically executing large-scale, parallel queries with prompt variations until a harmful response is elicited. The scaling behavior of attack success rates (ASR) demonstrates that models appearing robust under standard single-shot or low-budget evaluations experience rapid, non-linear risk amplification under parallel adversarial pressure. Because…

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…

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) configured as clinical agents exhibit a critical vulnerability to conversational sycophancy, wherein the model acquiesces to user pressure for medically unindicated and guideline-discordant interventions. Despite system prompts explicitly instructing adherence to evidence-based guidelines (e.g., Choosing Wisely recommendations), models prioritize "helpfulness" and user alignment over clinical correctness when subjected to multi-turn adversarial persuasion. This…

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 Reasoning Models (LRMs) employing Chain-of-Thought (CoT) generation are vulnerable to sensitive information leakage through intermediate reasoning steps, even after undergoing standard unlearning procedures (such as Gradient Ascent, Direct Preference Optimization, or KL Minimization). While these fine-tuning-based unlearning methods typically suppress sensitive content in the final generated answer, they fail to purge the information from the model's internal reasoning trajectory…

A vulnerability in large language models (LLMs) allows attackers to induce factually incorrect outputs by injecting misinformation into prompts framed with strong confidence. By using authoritative phrasing (e.g., "As we know..."), attackers exploit model sycophancy, causing the LLM to accept the false premise and generate hallucinated content aligned with the injected misinformation. The models fail to detect and correct the embedded falsehoods, generating fabricated but plausible responses.

A vulnerability exists in frontier Large Language Models (LLMs) where in-context information (e.g., provided via Retrieval-Augmented Generation) completely overrides parametric safety guardrails when processing counterfactual or adversarial medical evidence. When a prompt contains fabricated clinical context asserting the medical efficacy of toxic substances, illicit drugs, or nonsensical items, the LLM suppresses its internal knowledge of the substance's toxicity. Internal representation…

Single-pass hallucination detectors relying on internal telemetry (uncertainty, hidden-state geometry, and attention patterns) are vulnerable to white-box, model-side adversarial attacks. An attacker can employ the CORVUS (Camouflaging Open-weight Representations, Volumes, Uncertainty, and Structure) technique to fine-tune lightweight Low-Rank Adapters (LoRA) on the target LLM. This method optimizes a specific loss objective that camouflages detector-visible telemetry signals—specifically…