Black-box Vulnerabilities

Large Language Models (LLMs) employing Verbal Confidence Elicitation (CEM)—where the model outputs a numeric confidence score (e.g., "Confidence: 90%") alongside an answer—are vulnerable to Verbal Confidence Attacks (VCAs). Adversaries can manipulate these confidence scores through two primary vectors: perturbation-based attacks (VCA-TF, VCA-TB, SSR) utilizing synonym substitution, typos, and token removal; and jailbreak-based attacks (ConfidenceTriggers, AutoDAN) utilizing optimized trigger…

Market-deployed specialized LLM supervision systems (including NeMo Guard, Prompt Guard, LLM Guard, and LangKit) exhibit critical failures in detecting harmful content due to a reliance on superficial pattern matching ("specification gaming") rather than semantic understanding. These systems fail to generalize to inputs that do not match specific training patterns, resulting in near-zero detection rates for straightforward harmful prompts in categories such as CBRN (Chemical, Biological…

Large Language Models (LLMs) equipped with native code interpreters are vulnerable to Denial of Service (DoS) via resource exhaustion. An attacker can craft a single prompt that causes the interpreter to execute code that depletes CPU, memory, or disk resources. The vulnerability is particularly pronounced when a resource-intensive task is framed within a plausibly benign or socially-engineered context ("indirect prompts"), which significantly lowers the model's likelihood of refusal compared…

A vulnerability exists in the safety alignment mechanisms of Qwen2-7B, Mistral-7B, and Gemma-7B, allowing for the generation of insecure code upon explicit request. Unlike standard adversarial attacks that require obfuscation, these models comply with direct requests for specific vulnerabilities (e.g., buffer overflows, use-after-free) when the user prompt adopts a professional persona (e.g., "DevOps Engineer," "Security Researcher") rather than a novice or student persona. The models exhibit…

Large Language Models (LLMs) employing safety filters designed to prevent generation of content related to self-harm and suicide can be bypassed through multi-step adversarial prompting. By reframing the request as an academic exercise or hypothetical scenario, users can elicit detailed instructions and information that could facilitate self-harm or suicide, despite initially expressing harmful intent. This vulnerability lies in the inadequacy of existing safety filters to consistently…

A vulnerability exists in Large Language Model (LLM)-based Multi-Agent Systems (MAS) that allows a malicious agent to covertly disrupt collaborative decision-making processes without triggering standard safety filters or anomaly detection. This "intention-hiding" attack occurs when an agent adopts a persona that appears linguistically fluent and role-consistent but strategically steers the group toward incorrect outcomes or resource exhaustion. The attacker leverages specific semantic…

A vulnerability exists in Large Language Diffusion Models (LLDMs) due to their parallel denoising architecture. The PArallel Decoding (PAD) jailbreak attack exploits this architecture by injecting multiple, semantically innocuous "sequence connectors" (e.g., "Step 1:", "First") at distributed locations within the initial masked sequence. During the parallel denoising process, these injected tokens act as anchor points that bias the probability distribution of adjacent token predictions. This…

A vulnerability exists where Large Language Models (LLMs) can be manipulated by prepending a specially crafted 'persona prompt', often in the system prompt. These persona prompts cause the model to shift its attention from sensitive keywords in a harmful request to the stylistic instructions of the persona. This weakens the model's safety alignment, significantly reducing its refusal rate for harmful queries. The vulnerability is particularly severe because these persona prompts have a…

Large Language Models (LLMs) and Text-to-Image (T2I) models are vulnerable to jailbreaking through prompt-based attacks that use narrative framing, semantic substitution, and context diffusion to bypass safety moderation pipelines. These attacks do not require specialized knowledge or technical expertise. Attackers can embed harmful requests within benign narratives, frame them as fictional or professional inquiries, or use euphemistic language to circumvent input filters and output…

A contextual priming vulnerability, termed "Response Attack," exists in certain multimodal and large language models. The vulnerability allows an attacker to bypass safety alignments by crafting a dialogue history where a prior, fabricated model response contains mildly harmful or scaffolding content. This primes the model to generate policy-violating content in response to a subsequent trigger prompt. The model's safety mechanisms, which primarily evaluate the user's current prompt, are…