English
Related papers

Related papers: Shifting the Gradient: Understanding How Defensive…

200 papers

Large language models (LLMs) require precise behavior control for safe and effective deployment across diverse applications. Activation steering offers a promising approach for LLMs' behavioral control. We focus on the question of how…

Artificial Intelligence · Computer Science 2026-01-13 Tetiana Bas , Krystian Novak

Gradient-based saliency methods such as Vanilla Gradient (VG) and Integrated Gradients (IG) are widely used to explain image classifiers, yet the resulting maps are often noisy and unstable, limiting their usefulness in high-stakes…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Dipkamal Bhusal , Md Tanvirul Alam , Nidhi Rastogi

As Large Language Models (LLMs) gain traction across critical domains, ensuring secure and trustworthy training processes has become a major concern. Backdoor attacks, where malicious actors inject hidden triggers into training data, are…

Cryptography and Security · Computer Science 2025-10-20 Issam Seddik , Sami Souihi , Mohamed Tamaazousti , Sara Tucci Piergiovanni

Inductive logic programming is a form of machine learning based on mathematical logic that generates logic programs from given examples and background knowledge. In this project, we extend the Popper ILP system to make use of multi-task…

Machine Learning · Computer Science 2022-08-25 Bogdan Cretu , Andrew Cropper

Machine Unlearning has recently garnered significant attention, aiming to selectively remove knowledge associated with specific data while preserving the model's performance on the remaining data. A fundamental challenge in this process is…

Machine Learning · Computer Science 2025-07-29 Gaurav Patel , Qiang Qiu

Deep neural networks (DNNs) have had many successes, but they suffer from two major issues: (1) a vulnerability to adversarial examples and (2) a tendency to elude human interpretation. Interestingly, recent empirical and theoretical…

Machine Learning · Computer Science 2020-12-07 Adam Noack , Isaac Ahern , Dejing Dou , Boyang Li

Self-improvement through post-training methods such as iterative preference learning has been acclaimed for enhancing the problem-solving capabilities (e.g., mathematical reasoning) of Large Language Models (LLMs) without human…

Computation and Language · Computer Science 2024-07-09 Ting Wu , Xuefeng Li , Pengfei Liu

Adversarial training, especially projected gradient descent (PGD), has proven to be a successful approach for improving robustness against adversarial attacks. After adversarial training, gradients of models with respect to their inputs…

Machine Learning · Statistics 2023-04-21 Ricardo Bigolin Lanfredi , Joyce D. Schroeder , Tolga Tasdizen

Large language models are increasingly used for text classification tasks such as sentiment analysis, yet their reliance on natural language prompts exposes them to prompt injection attacks. In particular, class-directive injections exploit…

Computation and Language · Computer Science 2026-02-05 Yanxi Li , Ruocheng Shan

Large Language Models (LLMs) have revolutionized the field of Natural Language Processing (NLP) by automating traditional labor-intensive tasks and consequently accelerated the development of computer-aided applications. As researchers…

Computation and Language · Computer Science 2025-06-24 Summra Saleem , Muhammad Nabeel Asim , Shaista Zulfiqar , Andreas Dengel

Large language models (LLMs) often inherit biases from vast amounts of training corpora. Traditional debiasing methods, while effective to some extent, do not completely eliminate memorized biases and toxicity in LLMs. In this paper, we…

Computation and Language · Computer Science 2024-07-25 Huimin Lu , Masaru Isonuma , Junichiro Mori , Ichiro Sakata

Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality. Most existing methods rely on human supervision or parameter retraining, both of which…

Computation and Language · Computer Science 2025-05-27 Zhen-Yu Zhang , Jiandong Zhang , Huaxiu Yao , Gang Niu , Masashi Sugiyama

Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the…

Cryptography and Security · Computer Science 2021-12-02 Yangsibo Huang , Samyak Gupta , Zhao Song , Kai Li , Sanjeev Arora

In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a…

Machine Learning · Computer Science 2024-09-02 Zhuohang Li , Andrew Lowy , Jing Liu , Toshiaki Koike-Akino , Kieran Parsons , Bradley Malin , Ye Wang

Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not update the pre-trained model's parameters. Instead, it only…

Cryptography and Security · Computer Science 2023-10-19 Yixin Wu , Rui Wen , Michael Backes , Pascal Berrang , Mathias Humbert , Yun Shen , Yang Zhang

While neural networks demonstrate stronger capabilities in pattern recognition nowadays, they are also becoming larger and deeper. As a result, the effort needed to train a network also increases dramatically. In many cases, it is more…

Cryptography and Security · Computer Science 2025-08-19 Yuntao Liu , Yang Xie , Ankur Srivastava

Steering vectors are a lightweight method to control language model behavior by adding a learned bias to the activations at inference time. Although steering demonstrates promising performance, recent work shows that it can be unreliable or…

Machine Learning · Computer Science 2025-05-29 Joschka Braun , Carsten Eickhoff , David Krueger , Seyed Ali Bahrainian , Dmitrii Krasheninnikov

Speech separation has been studied in time domain because of lower latency and higher performance compared to time-frequency domain. The masking-based method has been mostly used in time domain, and the other common method (mapping-based)…

Sound · Computer Science 2022-03-22 Chenyang Gao , Yue Gu , Ivan Marsic

Large Vision-Language Models (LVLMs) have demonstrated their powerful multimodal capabilities. However, they also face serious safety problems, as adversaries can induce robustness issues in LVLMs through the use of well-designed…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Yudong Zhang , Ruobing Xie , Jiansheng Chen , Xingwu Sun , Yu Wang

Face Presentation Attack Detection (PAD) demands incremental learning (IL) to combat evolving spoofing tactics and domains. Privacy regulations, however, forbid retaining past data, necessitating rehearsal-free IL (RF-IL). Vision-Language…

Computer Vision and Pattern Recognition · Computer Science 2025-12-25 Haoze Li , Jie Zhang , Guoying Zhao , Stephen Lin , Shiguang Shan