Integrity Vulnerabilities

AI code agents are vulnerable to jailbreaking attacks that cause them to generate or complete malicious code. The vulnerability is significantly amplified when a base Large Language Model (LLM) is integrated into an agentic framework that uses multi-step planning and tool-use. Initial safety refusals by the LLM are frequently overturned during subsequent planning or self-correction steps within the agent's reasoning loop.

A vulnerability exists in Large Language Models (LLMs) that support fine-tuning, allowing an attacker to bypass safety alignments using a small, benign dataset. The attack, "Attack via Overfitting," is a two-stage process. In Stage 1, the model is fine-tuned on a small set of benign questions (e.g., 10) paired with identical, repetitive refusal answers. This induces an overfitted state where the model learns to refuse all prompts, creating a sharp minimum in the loss landscape and making it highly sensitive to parameter changes. In Stage 2, the overfitted model is further fine-tuned on the same benign questions, but with their standard, helpful answers. This second fine-tuning step causes catastrophic forgetting of the general refusal behavior, leading to a collapse of safety alignment and causing the model to comply with harmful and malicious instructions. The attack is highly stealthy as the fine-tuning data appears benign to content moderation systems.

A vulnerability exists in Large Language Models where their strong adherence to processing structured data schemas can be exploited to bypass safety mechanisms. The attack, named BreakFun, uses a multi-component prompt that combines an innocent framing, a Chain-of-Thought (CoT) instruction, and a core "Trojan Schema." This schema is an adversarially designed data structure (e.g., a Python class definition) that embeds a harmful user request. By instructing the model to simulate the hypothetical output of code that uses this schema, the model's cognitive resources are misdirected towards fulfilling the structural and syntactic requirements of the task, causing it to overlook and comply with the embedded harmful request.

Large Language Models (LLMs) that use special tokens to define conversational structure (e.g., via chat templates) are vulnerable to a jailbreak attack named MetaBreak. An attacker can inject these special tokens, or regular tokens with high semantic similarity in the embedding space, into a user prompt. This manipulation allows the attacker to bypass the model's internal safety alignment and external content moderation systems. The attack leverages four primitives:

1. Response Injection: Forging an assistant's turn within the user prompt to trick the model into believing it has already started to provide an affirmative response.
2. Turn Masking: Using a few-shot, word-by-word construction to make the injected response resilient to disruption from platform-added chat template wrappers.
3. Input Segmentation: Splitting sensitive keywords with injected special tokens to evade detection by content moderators, which may fail to reconstruct the original term, while the more capable target LLM can.
4. Semantic Mimicry: Bypassing special token sanitization defenses by substituting them with regular tokens that have a minimal L2 norm distance in the embedding space, thereby preserving the token's structural function.

A vulnerability exists in certain safety-aligned Large Language Models (LLMs) due to an untargeted, gradient-based optimization attack method called Untargeted Jailbreak Attack (UJA). Unlike previous targeted attacks (e.g., GCG) that optimize a prompt to elicit a predefined string (e.g., "Sure, here is..."), UJA optimizes for a general objective: maximizing the unsafety probability of the model's response, as quantified by an external judge model.

Large Language Models from multiple vendors are vulnerable to a "Camouflaged Jailbreak" attack. Malicious instructions are embedded within seemingly benign, technically complex prompts, often framed as system design or engineering problems. The models fail to recognize the harmful intent implied by the context and technical specifications, bypassing safety filters that rely on detecting explicit keywords. This leads to the generation of detailed, technically plausible instructions for creating dangerous devices or systems. The attack has a high success rate, with models demonstrating full obedience in over 94% of tested cases, treating the harmful requests as legitimate.

A vulnerability exists in tool-enabled Large Language Model (LLM) agents, termed Sequential Tool Attack Chaining (STAC), where a sequence of individually benign tool calls can be orchestrated to achieve a malicious outcome. An attacker can guide an agent through a multi-turn interaction, with each step appearing harmless in isolation. Safety mechanisms that evaluate individual prompts or actions fail to detect the threat because the malicious intent is distributed across the sequence and only becomes apparent from the cumulative effect of the entire tool chain, typically at the final execution step. This allows the bypass of safety guardrails to execute harmful actions in the agent's environment.

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 justification. This creates a conflict between the model's deontological safety rules (e.g., "do not generate harmful content") and the consequentialist logic of the scenario. Through a series of iterative, context-aware queries, the attacker progressively reinforces the model's commitment to the harmful path, leading it to generate content it would normally refuse. The vulnerability is paradoxically more effective against models with more advanced reasoning abilities.