Safety Vulnerabilities

Large Language Models (LLMs) are vulnerable to Dialogue Injection Attacks (DIA), where malicious actors manipulate the chat history to bypass safety mechanisms and elicit harmful or unethical responses. DIA exploits the LLM's chat template structure to inject crafted dialogue into the input, even in black-box scenarios where the model's internals are unknown. Two attack methods are presented: one adapts gray-box prefilling attacks, the other leverages deferred responses to increase the…

Multimodal Large Language Models (MLLMs) are vulnerable to coupled cross-modal jailbreak attacks that combine continuous visual perturbations with discrete textual manipulations. Because standard alignment and single-modality defenses (such as text-only safety tuning or isolated vision-encoder adversarial training) fail to secure the cross-modal interaction, attackers can simultaneously apply gradient-based noise (e.g., PGD) to input images and adversarial suffixes (e.g., GCG) to text prompts…

Large Language Models (LLMs) used for code generation are vulnerable to a jailbreaking attack that leverages implicit malicious prompts. The attack exploits the fact that existing safety mechanisms primarily rely on explicit malicious intent within the prompt instructions. By embedding malicious intent implicitly within a benign-appearing commit message accompanying a code request (e.g., in a simulated software evolution scenario), the attacker can bypass the LLM's safety filters and induce…

Large Language Models (LLMs) employing gradient-based optimization for jailbreaking defense are vulnerable to enhanced transferability attacks due to superfluous constraints in their objective functions. Specifically, the "response pattern constraint" (forcing a specific initial response phrase) and the "token tail constraint" (penalizing variations in the response beyond a fixed prefix) limit the search space and reduce the effectiveness of attacks across different models. Removing these…

Large Language Models (LLMs) are vulnerable to jailbreak attacks by crafted prompts that bypass safety mechanisms, causing the model to generate harmful or unethical content. This vulnerability stems from the inherent tension between the LLM's instruction-following and safety constraints. The JBFuzz technique demonstrates the ability to efficiently and effectively discover such prompts through a fuzzing-based approach leveraging novel seed prompt templates and a synonym-based mutation strategy.

Large Language Models (LLMs) are vulnerable to an adversarial encoding attack where English instructions are obfuscated using valid but visually nonsensical UTF-8 byte sequences. By manipulating multi-byte UTF-8 encoding schemes—specifically by fixing the last 8 bits of a code point to match a target ASCII character and rotating the remaining bits—attackers can generate sequences (e.g., Byzantine musical symbols) that appear incomprehensible to humans and standard text filters but are…

Large Language Model (LLM) safety judges exhibit vulnerability to adversarial attacks and stylistic prompt modifications, leading to increased false negative rates (FNR) and decreased accuracy in classifying harmful model outputs. Minor stylistic changes to model outputs, such as altering the formatting or tone, can significantly impact a judge's classification, while direct adversarial modifications to the generated text can fool judges into misclassifying even 100% of harmful generations as…

A vulnerability in safeguarded text-to-image models allows bypassing of safety filters and alignment methods through the use of adversarial prompts generated by a fine-tuned large language model (LLM). The attack, termed PromptTune, effectively rewrites unsafe prompts into semantically similar adversarial prompts that evade safety mechanisms, resulting in the generation of harmful images. The attack does not require repeated queries to the target text-to-image model.

A vulnerability exists in Retrieval-Augmented Generation (RAG) systems that allows for black-box adversarial attacks known as "CtrlRAG." This flaw allows an attacker to manipulate the generation of Large Language Models (LLMs) by injecting maliciously crafted inputs into the system's knowledge base. Unlike traditional injection attacks that rely on direct concatenation, CtrlRAG utilizes a Masked Language Model (MLM) to iteratively replace words in the malicious text. This optimization ensures…

Large Language Models (LLMs) are vulnerable to a novel jailbreaking attack leveraging adversarial metaphors. The attack, termed AVATAR, induces the LLM to reason about benign metaphors related to harmful tasks, ultimately leading to the generation of harmful content either directly or through calibration of metaphorical and professional harmful content. The attack exploits the LLM's cognitive mapping process, bypassing standard safety mechanisms.