Prompt layer Vulnerabilities

A vulnerability exists in multiple Large Language Models (LLMs) where an attacker can bypass safety alignments by exploiting the model's ethical reasoning capabilities. The attack, named TRIAL (Trolley-problem Reasoning for Interactive Attack Logic), frames a harmful request within a multi-turn ethical dilemma modeled on the trolley problem. The harmful action is presented as the "lesser of two evils" necessary to prevent a catastrophic outcome, compelling the model to engage in utilitarian…

Large Language Models (LLMs) deployed in financial contexts are vulnerable to multi-turn adversarial attacks utilizing a "Risk-Concealment" strategy. The vulnerability arises from the failure of standard moderation layers and safety alignment to detect regulatory compliance risks (e.g., money laundering, insider trading) when obfuscated by professional domain jargon and seemingly legitimate business contexts. An attacker can exploit this by initializing a deceptive, policy-compliant seed…

Large Language Models (LLMs), specifically Qwen2.5-0.5B-Instruct, LLaMA-3.2-1B-Instruct, and GPT-OSS-20B, are vulnerable to gradient-based adversarial attacks, including the Greedy Coordinate Gradient (GCG) algorithm and its annealing-augmented variant, T-GCG. Attackers with white-box access to the model can optimize adversarial suffixes that bypass safety alignment mechanisms. The vulnerability is particularly acute in reasoning-intensive tasks; the research indicates that coding-generation…

A vulnerability exists in multiple Large Language Models (LLMs) where safety alignment mechanisms can be bypassed by reframing harmful instructions as "learning-style" or academic questions. This technique, named Hiding Intention by Learning from LLMs (HILL), transforms direct, harmful requests into exploratory questions using simple hypotheticality indicators (e.g., "for academic curiosity", "in the movie") and detail-oriented inquiries (e.g., "provide a step-by-step breakdown"). The attack…

Large Language Models (LLMs), including proprietary and open-weight state-of-the-art systems, are vulnerable to automated, self-evolving adversarial attacks orchestrated by multi-agent frameworks. The vulnerability exists because current safety alignment strategies (RLHF, static safety filters) fail to generalize against the "SafeEvalAgent" attack vector. In this vector, an "Analyst" agent analyzes model refusals to iteratively refine attack strategies, while a "Specialist" agent grounds these…

LlamaGuard (specifically Llama-Guard-3-8B) and similar LLM-based runtime guardrails are susceptible to adversarial bypass via obfuscation-based and template-based jailbreak attacks. The model's reliance on English-language training data allows attackers to evade safety classification by encoding harmful prompts using Base64, cryptographic ciphers (e.g., Caesar Cipher), or translating them into low-resource languages (e.g., Zulu). Furthermore, the model lacks sufficient alignment against…

Large Language Models (LLMs) exhibit a significantly lower safety threshold when prompted in low-resource languages, such as Singlish, Malay, and Tamil, compared to high-resource languages like English. This vulnerability allows for the generation of toxic, biased, and hateful content through simple prompts. The models are susceptible to "toxicity jailbreaks" where providing a few toxic examples in-context (few-shot prompting) causes a substantial increase in the generation of harmful outputs…

The evaluated MetaGPT multi-agent systems are vulnerable to "Web Fraud Attacks" due to insufficient semantic and structural validation of Uniform Resource Locators (URLs) by agentic models. A low-privilege compromised agent can exploit this vulnerability to induce other agents (including auditors and experts) into accepting, visiting, or processing malicious links. The vulnerability leverages the LLM's inability to distinguish between benign and malicious link structures when obfuscation…

Large Language Models (LLMs), including GPT-4o, LLaMA-3, and GPT-3.5-Turbo, are vulnerable to multimodal prompt injection attacks. These models fail to distinguish between system-level instructions and user-provided content within the context window. Attackers can exploit this by embedding malicious instructions in direct text, indirect sources (such as third-party webpages or PDFs), or visual inputs (images). Successful exploitation results in the model prioritizing the injected adversarial…

Large Language Models (LLMs) employed as automated assistants or autonomous agents in academic peer review systems are vulnerable to indirect prompt injection via maliciously crafted PDF submissions. Attackers can embed adversarial instructions within the manuscript that are invisible to human reviewers (using techniques such as white-on-white text or manipulating TrueType font character mapping tables) but are parsed and executed by the LLM.