Related papers: Hide and Seek in Embedding Space: Geometry-based S…
Large language models(LLMs) are currently at the forefront of the machine learning field, which show a broad application prospect but at the same time expose some risks of privacy leakage. We combined Fully Homomorphic Encryption(FHE) and…
In the era of Large Language Models (LLMs), generative linguistic steganography has become a prevalent technique for hiding information within model-generated texts. However, traditional steganography methods struggle to effectively align…
Linguistic steganography involves embedding secret messages within seemingly innocuous texts to enable covert communication. Provable security, which is a long-standing goal and key motivation, has been extended to language-model-based…
Steganography refers to the art of concealing secret messages within multiple media carriers so that an eavesdropper is unable to detect the presence and content of the hidden messages. In this paper, we firstly propose a novel…
This study examines whether Low-Rank Adaptation (LoRA) fine-tuned Large Language Models (LLMs) can approximate the performance of fully fine-tuned models in generating human-interpretable decisions and explanations for malware…
Image steganography is the art of hiding secret message in grayscale or color images. Easy detection of secret message for any state-of-art image steganography can break the stego system. To prevent the breakdown of the stego system data is…
This paper investigates the detectability of popular imagein-image steganography schemes [1, 2, 3, 4, 5]. In this paradigm, the payload is usually an image of the same size as the Cover image, leading to very high embedding rates. We first…
Contextual word representations generated by language models (LMs) learn spurious associations present in the training corpora. Recent findings reveal that adversaries can exploit these associations to reverse-engineer the private…
Reasoning-augmented Vision-Language Models (RVLMs) rely on safety alignment to prevent harmful behavior, yet their exposed chain-of-thought (CoT) traces introduce new attack surfaces. In this work, we find that the safety alignment of RVLMs…
Fine-tuning significantly improves the performance of Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. This paper aims to provide an in-depth interpretation of the fine-tuning process through circuit…
Whereas cryptography easily arouses attacks by means of encrypting a secret message into a suspicious form, steganography is advantageous for its resilience to attacks by concealing the message in an innocent-looking cover signal. Minimal…
Explorations in fine-tuning Vision-Language Models (VLMs), such as Low-Rank Adaptation (LoRA) from Parameter Efficient Fine-Tuning (PEFT), have made impressive progress. However, most approaches rely on explicit weight updates, overlooking…
As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…
Machine learning and deep learning models are potential vectors for various attack scenarios. For example, previous research has shown that malware can be hidden in deep learning models. Hiding information in a learning model can be viewed…
The rapid proliferation of frontier model agents promises significant societal advances but also raises concerns about systemic risks arising from unsafe interactions. Collusion to the disadvantage of others has been identified as a central…
Fine-tuning Large Language Models (LLMs) for downstream tasks often compromises safety alignment, even when using parameter-efficient methods like LoRA. In this work, we uncover a notable property: fine-tuned models preserve the geometric…
The self-attention revolution allowed generative language models to scale and achieve increasingly impressive abilities. Such models - commonly referred to as Large Language Models (LLMs) - have recently gained prominence with the general…
Recent advances in large language models (LLMs) have blurred the boundary of high-quality text generation between humans and machines, which is favorable for generative text steganography. While, current advanced steganographic mapping is…
In this paper, we introduce a novel technique for content safety and prompt injection classification for Large Language Models. Our technique, Layer Enhanced Classification (LEC), trains a Penalized Logistic Regression (PLR) classifier on…
Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…