Language Model Security Database

Large Language Models (LLMs), even those initially aligned for safety, are vulnerable to having their safety mechanisms compromised through fine-tuning on a small number of adversarially-crafted or even seemingly benign sentences. Fine-tuning with as few as 10 toxic sentences can significantly increase the model's compliance with harmful instructions.

AdvBDGen demonstrates a novel backdoor attack against LLMs aligned using Reinforcement Learning with Human Feedback (RLHF). The attack generates prompt-specific, fuzzy backdoor triggers, enhancing stealth and resistance to removal compared to traditional constant triggers. The attacker manipulates prompts and preference labels in a subset of RLHF training data to install these triggers. The triggers are designed to evade detection by a "weak" discriminator LLM while being detectable by a…

Large Language Models (LLMs) are vulnerable to jailbreaking via the addition of adversarial suffixes generated by models like AmpleGCG-Plus. These suffixes, often consisting of gibberish or nonsensical text, cause the LLM to bypass safety protocols and generate harmful or undesired outputs. The vulnerability stems from the LLM's inability to reliably identify and filter these adversarial suffixes, even when they lack semantic meaning. AmpleGCG-Plus significantly improves the success rate and…

Multimodal fusion models, such as Chameleon models, utilize non-differentiable tokenization functions for image inputs, hindering direct gradient-based attacks. This vulnerability allows attackers with white-box access to bypass safety mechanisms by using a "tokenizer shortcut," a differentiable approximation of the tokenization process, to perform continuous optimization of image inputs. This enables the generation of adversarial images that elicit harmful responses from the model, even for…

Large Language Models (LLMs) are vulnerable to jailbreak attacks utilizing a novel Functional Homotopy (FH) optimization method. FH exploits the functional duality between model training and input generation, iteratively solving a series of "easy-to-hard" optimization problems to generate adversarial prompts that circumvent safety mechanisms and elicit undesirable model responses. This is achieved by first misaligning the model via gradient descent on continuous parameters, then leveraging…

Large Language Models (LLMs) are vulnerable to an attack vector termed "Attack via Implicit Reference" (AIR). AIR bypasses safety mechanisms by decomposing a malicious objective into multiple benign, seemingly unrelated objectives linked through implicit contextual references. The LLM generates harmful content by combining the outputs of these seemingly harmless objectives, without explicitly triggering safety filters designed to detect direct requests for malicious content.

A Chain-of-Jailbreak (CoJ) attack allows bypassing safety mechanisms in image generation models by iteratively editing images based on a sequence of sub-queries. The attack decomposes a malicious query into multiple, seemingly benign sub-queries, each causing the model to generate and modify an image, ultimately producing harmful content. Successful attacks leverage various editing operations (insert, delete, change) on different elements (words, characters, images).

Large Language Models (LLMs) are vulnerable to a novel jailbreak attack that exploits resource limitations. By overloading the model with a computationally intensive preliminary task (e.g., a complex character map lookup and decoding), the attacker prevents the activation of the LLM's safety mechanisms, enabling the generation of unsafe outputs from subsequent prompts. The attack's strength is scalable and adjustable by modifying the complexity of the preliminary task.

Large Language Models (LLMs) exhibit a left-to-right processing bias, making them vulnerable to "FlipAttack." This attack disguises a harmful prompt by flipping (reversing) the order of characters or words, thereby reducing the LLM’s comprehension of the harmful content. A "flipping guidance" module then instructs the LLM to reverse the flipped text, revealing and executing the original harmful prompt.

Large Language Models (LLMs) are vulnerable to a multi-objective black-box jailbreaking attack (BlackDAN) that optimizes prompts to maximize the likelihood of generating unsafe responses while maintaining contextual relevance and minimizing detectability. The attack leverages a multi-objective evolutionary algorithm (NSGA-II) to balance attack success rate, semantic consistency, and stealthiness, resulting in more effective and less easily detectable jailbreaks than single-objective approaches.