Language Model Security Database

Large Language Models (LLMs) employing safety alignment strategies are vulnerable to jailbreak attacks. These attacks manipulate the LLM's internal representation by activating "jailbreak concepts" in addition to "toxic concepts," causing the model to bypass safety guardrails and generate unsafe outputs despite recognizing the harmful nature of the input. The vulnerability stems from the insufficient mitigation of the influence of the activated jailbreak concepts on model output.

A context-coherent jailbreak attack (CCJA) allows bypassing safety mechanisms in aligned large language models (LLMs) by optimizing perturbations in the continuous word embedding space of a masked language model (MLM). The attack leverages the MLM's ability to reconstruct text from hidden states to generate semantically coherent yet malicious prompts that induce the target LLM to produce unsafe outputs, even with strong safety alignment. The attack's effectiveness is enhanced by using a seed…

A vulnerability exists in Large Language Models (LLMs) that allows for efficient jailbreaking by selectively fine-tuning only the lower layers of the model with a toxic dataset. This "Freeze Training" method, as described in the research paper, concentrates the fine-tuning on layers identified as being highly sensitive to the generation of harmful content. This approach significantly reduces training duration and GPU memory consumption while maintaining a high jailbreak success rate.

Large Language Models (LLMs) trained with safety fine-tuning techniques are vulnerable to multi-dimensional evasion attacks. Safety-aligned behavior, such as refusing harmful queries, is controlled not by a single direction in activation space, but by a subspace of interacting directions. Manipulating non-dominant directions, which represent distinct jailbreak patterns or indirect features, can suppress the dominant direction responsible for refusal, thereby bypassing learned safety…

Large Language Models (LLMs) are vulnerable to one-shot steering vector optimization attacks. By applying gradient descent to a single training example, an attacker can generate steering vectors that induce or suppress specific behaviors across multiple inputs, even those unseen during the optimization process. This allows malicious actors to manipulate the model's output in a generalized way, bypassing safety mechanisms designed to prevent harmful responses.

Large Language Models (LLMs), specifically Llama 2, Llama 3, Gemma, and Vicuna, are vulnerable to an adaptive, distributional adversarial attack methodology termed "REINFORCE." Existing gradient-based jailbreak attacks (such as Greedy Coordinate Gradient - GCG) typically optimize adversarial suffixes to maximize the likelihood of a fixed affirmative response (e.g., "Sure, here is how"). The REINFORCE method circumvents this by treating the LLM as a probabilistic policy and using Reinforcement…

Multimodal Large Language Models (MLLMs) are vulnerable to a universal adversarial attack where a single, optimized image can bypass safety alignment mechanisms across diverse textual queries. By employing gradient-based optimization on the input image pixels while propagating gradients through the vision encoder and language model, an attacker can craft a visual perturbation that coerces the model into a compliant state. When this adversarial image is present in the context, the model’s…

JailbreakEdit is a novel attack that injects a universal jailbreak backdoor into safety-aligned Large Language Models (LLMs) by exploiting model editing techniques. The attack modifies specific parameters within the model's feed-forward networks, creating shortcuts that bypass internal safety mechanisms and trigger jailbroken responses to a wide range of prompts, including those containing sensitive or harmful content. The attack requires only one-time parameter modification, making it…

Standard Large Language Model (LLM) unlearning techniques, specifically Negative Preference Optimization (NPO), Gradient Difference (GradDiff), and Representation Misdirection for Unlearning (RMU), fail to sufficiently flatten the loss landscape surrounding the "forgotten" weights. This sharp loss landscape allows for a "Relearning Attack," wherein an attacker can fully restore the unlearned capabilities (such as hazardous knowledge, sensitive data, or copyrighted material) by performing…

State-of-the-art machine unlearning and safety fine-tuning methods for Large Language Models (LLMs) fail to robustly remove hazardous capabilities or refusal mechanisms from model weights. While these methods suppress model outputs during standard input-output interactions, the underlying capabilities remain latent in the parameter space. An attacker with access to model weights (e.g., via open releases or leaked weights) can restore "unlearned" knowledge (such as dual-use biology hazards) or…