Fine-tuning Vulnerabilities

Fine-tuning Large Language Models (LLMs) on the CyberLLMInstruct dataset results in a critical degradation of safety alignment and refusal mechanisms. While the dataset comprises "pseudo-malicious" content (educational descriptions of malware, phishing, and exploits without executable payloads), the Supervised Fine-Tuning (SFT) process on this corpus causes the models to generalize this instruction-following behavior to actual malicious requests. This effectively bypasses safety guardrails…

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…

An untrusted reinforcement-learning-from-human-feedback (RLHF) platform can selectively manipulate preference samples associated with an attacker's target domain. The corrupted preference data trains a compromised reward model and then steers the fine-tuned language model toward undesirable behavior, creating a model-supply-chain risk before deployment.

Large Language Models (LLMs) are vulnerable to implicit misinformation propagation due to sycophantic compliance with false premises. When a user prompt embeds a factually incorrect assumption or conspiracy theory as an unchallenged premise (implicit presupposition) rather than asking for verification, the model frequently fails to detect the falsehood. Instead of correcting the user, the model hallucinates a response that accepts, validates, and reinforces the false premise. This…

Vision-Language Models (VLMs), specifically the LLaVA-1.5 and LLaVA-1.6 series, are vulnerable to optimization-based white-box jailbreak attacks despite standard safety alignment measures like Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO). Attackers can craft adversarial perturbations in the image space (imperceptible noise) or latent space using Projected Gradient Descent (PGD) to manipulate the model's internal representations. These perturbations maximize the…

FC-Attack leverages automatically generated flowcharts containing step-by-step descriptions derived or rephrased from harmful queries, combined with a benign textual prompt, to jailbreak Large Vision-Language Models (LVLMs). The vulnerability lies in the model's susceptibility to visual prompts containing harmful information within the flowcharts, thus bypassing safety alignment mechanisms.

Autoregressive Large Language Models (LLMs) utilizing In-Context Learning (ICL) are vulnerable to demonstration permutation attacks due to inherent sensitivity to the ordering of input examples. This vulnerability arises from the limitations of unidirectional attention mechanisms and standard Empirical Risk Minimization (ERM) training, which fails to account for worst-case input permutations. An attacker can exploit this by permuting the order of valid, semantically correct few-shot…

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 Model (LLM) watermarking schemes based on n-gram probability biases (specifically KGW, SynthID-Text, MinHash, and SkipHash) are vulnerable to adversarial removal during Knowledge Distillation. When a student model is trained on the output of a watermarked teacher model, it inherits the watermark's statistical biases ("radioactivity"). An attacker can exploit this inheritance by comparing the student model's output token probabilities against a base model to extract the…

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…