English
Related papers

Related papers: Adaptive Defense against Harmful Fine-Tuning for L…

200 papers

Large Language Models (LLMs) generating unsafe responses to toxic prompts is a significant issue in their applications. While various efforts aim to address this safety concern, previous approaches often demand substantial human data…

Computation and Language · Computer Science 2024-12-12 Yuxiao Lu , Arunesh Sinha , Pradeep Varakantham

Failure-Directed Search (FDS) is a significant complete generic search algorithm used in Constraint Programming (CP) to efficiently explore the search space, proven particularly effective on scheduling problems. This paper analyzes FDS's…

Machine Learning · Computer Science 2025-08-28 Vilém Heinz , Petr Vilím , Zdeněk Hanzálek

Data Poisoning (DP) is an effective attack that causes trained classifiers to misclassify their inputs. DP attacks significantly degrade a classifier's accuracy by covertly injecting attack samples into the training set. Broadly applicable…

Machine Learning · Computer Science 2022-05-13 Xi Li , David J. Miller , Zhen Xiang , George Kesidis

Due to the computational complexity of evaluating interatomic forces from first principles, the creation of interatomic machine learning force fields has become a highly active field of research. However, the generation of training datasets…

Machine Learning · Computer Science 2025-07-21 Tim Rensmeyer , Denis Kramer , Oliver Niggemann

Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical and theoretical, training deep learning models robust to…

Machine Learning · Computer Science 2024-02-29 Luca Bortolussi , Ginevra Carbone , Luca Laurenti , Andrea Patane , Guido Sanguinetti , Matthew Wicker

Large-scale language models achieved state-of-the-art performance over a number of language tasks. However, they fail on adversarial language examples, which are sentences optimized to fool the language models but with similar semantic…

Computation and Language · Computer Science 2023-10-31 Noah Thomas McDermott , Junfeng Yang , Chengzhi Mao

This work analyzes how attention-based Bidirectional Long Short-Term Memory (BLSTM) models adapt to noise-augmented speech. We identify crucial components for noise adaptation in BLSTM models by freezing model components during fine-tuning.…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-27 Coleman Hooper , Thierry Tambe , Gu-Yeon Wei

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

Computation and Language · Computer Science 2024-06-12 Fan Liu , Zhao Xu , Hao Liu

Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…

Computer Vision and Pattern Recognition · Computer Science 2023-04-05 Ajinkya Tejankar , Maziar Sanjabi , Qifan Wang , Sinong Wang , Hamed Firooz , Hamed Pirsiavash , Liang Tan

Backdoor attacks have posed a significant threat to the security of deep neural networks (DNNs). Despite considerable strides in developing defenses against backdoor attacks in the visual domain, the specialized defenses for the audio…

Sound · Computer Science 2025-02-04 Nanjun Zhou , Weilin Lin , Li Liu

Performance tuning of Database Management Systems(DBMS) is both complex and challenging as it involves identifying and altering several key performance tuning parameters. The quality of tuning and the extent of performance enhancement…

Databases · Computer Science 2010-05-07 S. F. Rodd , U. P. Kulkarni

Controller tuning and parameter optimization are crucial in system design to improve closed-loop system performance. Bayesian optimization has been established as an efficient model-free controller tuning and adaptation method. However,…

Systems and Control · Electrical Eng. & Systems 2024-04-24 Christopher König , Raamadaas Krishnadas , Efe C. Balta , Alisa Rupenyan

The emergence of deep learning models has revolutionized various industries over the last decade, leading to a surge in connected devices and infrastructures. However, these models can be tricked into making incorrect predictions with high…

Machine Learning · Computer Science 2025-09-03 Pooja Krishan , Rohan Mohapatra , Sanchari Das , Saptarshi Sengupta

Mainstream backdoor attack methods typically demand substantial tuning data for poisoning, limiting their practicality and potentially degrading the overall performance when applied to Large Language Models (LLMs). To address these issues,…

Cryptography and Security · Computer Science 2024-03-21 Yanzhou Li , Tianlin Li , Kangjie Chen , Jian Zhang , Shangqing Liu , Wenhan Wang , Tianwei Zhang , Yang Liu

Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However, if the third-party providers are untrusted, they can…

Cryptography and Security · Computer Science 2024-01-10 Han Qiu , Yi Zeng , Shangwei Guo , Tianwei Zhang , Meikang Qiu , Bhavani Thuraisingham

Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…

Computation and Language · Computer Science 2024-10-15 Minjun Zhu , Linyi Yang , Yifan Wei , Ningyu Zhang , Yue Zhang

Large Language Models (LLMs) increasingly rely on automatic prompt engineering in graphical user interfaces (GUIs) to refine user inputs and enhance response accuracy. However, the diversity of user requirements often leads to unintended…

Computation and Language · Computer Science 2025-06-24 Chong Zhang , Xiang Li , Jia Wang , Shan Liang , Haochen Xue , Xiaobo Jin

With the rapid development of generative artificial intelligence, particularly large language models a number of sub-fields of deep learning have made significant progress and are now very useful in everyday applications. For…

Machine Learning · Computer Science 2025-04-23 Orson Mengara

In this work, we aim to enhance the system robustness of end-to-end automatic speech recognition (ASR) against adversarially-noisy speech examples. We focus on a rigorous and empirical "closed-model adversarial robustness" setting (e.g.,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-18 Chao-Han Huck Yang , Zeeshan Ahmed , Yile Gu , Joseph Szurley , Roger Ren , Linda Liu , Andreas Stolcke , Ivan Bulyko

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…

Cryptography and Security · Computer Science 2022-05-31 Sangeet Sagar , Abhinav Bhatt , Abhijith Srinivas Bidaralli