English
Related papers

Related papers: Hide and Seek in Embedding Space: Geometry-based S…

200 papers

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…

Cryptography and Security · Computer Science 2025-01-08 Zhang Ruoyan , Zheng Zhongxiang , Bao Wankang

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…

Cryptography and Security · Computer Science 2024-12-17 Minhao Bai , Jinshuai Yang , Kaiyi Pang , Yongfeng Huang , Yue Gao

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…

Computation and Language · Computer Science 2026-04-14 Ruiyi Yan , Yugo Murawaki

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…

Cryptography and Security · Computer Science 2019-06-05 Zheng Li , Ge Han , Yunqing Wei , Shanqing Guo

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…

Cryptography and Security · Computer Science 2025-11-26 Stephen C. Gravereaux , Sheikh Rabiul Islam

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…

Multimedia · Computer Science 2022-01-05 Soumendu Chakraborty , Anand Singh Jalal , Charul Bhatnagar

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…

Cryptography and Security · Computer Science 2026-03-13 Antoine Mallet , Patrick Bas

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…

Computation and Language · Computer Science 2021-12-08 Geetanjali Bihani

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…

Computation and Language · Computer Science 2026-03-10 Le Yu , Zhengyue Zhao , Yawen Zheng , Yunhao Liu

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…

Computation and Language · Computer Science 2025-06-16 Xu Wang , Yan Hu , Wenyu Du , Reynold Cheng , Benyou Wang , Difan Zou

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…

Cryptography and Security · Computer Science 2022-10-27 Kejiang Chen , Hang Zhou , Yaofei Wang , Menghan Li , Weiming Zhang , Nenghai Yu

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…

Machine Learning · Computer Science 2025-12-30 Mingyuan Zhang , Yue Bai , Yifan Wang , Yiyang Huang , Yun Fu

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 · Computer Science 2025-05-16 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

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…

Machine Learning · Computer Science 2023-08-31 Rishit Agrawal , Kelvin Jou , Tanush Obili , Daksh Parikh , Samarth Prajapati , Yash Seth , Charan Sridhar , Nathan Zhang , Mark Stamp

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…

Computation and Language · Computer Science 2025-12-03 Yohan Mathew , Ollie Matthews , Robert McCarthy , Joan Velja , Christian Schroeder de Witt , Dylan Cope , Nandi Schoots

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…

Machine Learning · Computer Science 2025-11-25 Thong Bach , Thanh Nguyen-Tang , Dung Nguyen , Thao Minh Le , Truyen Tran

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…

Computation and Language · Computer Science 2023-04-19 Da Silva Gameiro Henrique , Andrei Kucharavy , Rachid Guerraoui

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…

Computation and Language · Computer Science 2024-11-06 Jiaxuan Wu , Zhengxian Wu , Yiming Xue , Juan Wen , Wanli Peng

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…

Computation and Language · Computer Science 2024-12-19 Mason Sawtell , Tula Masterman , Sandi Besen , Jim Brown

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…

Computation and Language · Computer Science 2025-01-31 Sunbowen Lee , Shiwen Ni , Chi Wei , Shuaimin Li , Liyang Fan , Ahmadreza Argha , Hamid Alinejad-Rokny , Ruifeng Xu , Yicheng Gong , Min Yang