English
Related papers

Related papers: Shifting the Gradient: Understanding How Defensive…

200 papers

During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, existing defense strategies suffer from limited…

Cryptography and Security · Computer Science 2025-10-13 Shuai Zhao , Xinyi Wu , Shiqian Zhao , Xiaobao Wu , Zhongliang Guo , Yanhao Jia , Anh Tuan Luu

The incredible effectiveness of adversarial attacks on fooling deep neural networks poses a tremendous hurdle in the widespread adoption of deep learning in safety and security-critical domains. While adversarial defense mechanisms have…

Machine Learning · Computer Science 2020-11-20 Hossein Aboutalebi , Mohammad Javad Shafiee Alexander Wong

Prompt injection attacks are an emerging threat to large language models (LLMs), enabling malicious users to manipulate outputs through carefully designed inputs. Existing detection approaches often require centralizing prompt data,…

Cryptography and Security · Computer Science 2025-11-18 Hasini Jayathilaka

Large language models are increasingly used as computational tools for modeling human-like behavior. We introduce a behavioral induction framework that modifies model policies through fine-tuning on structured decision-making tasks: using…

Computation and Language · Computer Science 2026-05-22 Nicola Milano , Davide Marocco

Gradient clipping is widely used to stabilize deep network training, but its formulation as a hard, fixed threshold limits flexibility and ignores gradient distribution dynamics. We propose SPAMP (Statistical Per-layer Adaptive Modulation…

Machine Learning · Computer Science 2025-10-03 Haochen You , Baojing Liu

Deep learning-based Natural Language Processing (NLP) models are vulnerable to adversarial attacks, where small perturbations can cause a model to misclassify. Adversarial Training (AT) is often used to increase model robustness. However,…

Computation and Language · Computer Science 2024-10-15 Vyas Raina , Samson Tan , Volkan Cevher , Aditya Rawal , Sheng Zha , George Karypis

The performance of Large Language Models (LLMs) on natural language tasks can be improved through both supervised fine-tuning (SFT) and in-context learning (ICL), which operate via distinct mechanisms. Supervised fine-tuning updates the…

Computation and Language · Computer Science 2025-05-21 Saahith Janapati , Yangfeng Ji

Counterfactual Learning to Rank (LTR) algorithms learn a ranking model from logged user interactions, often collected using a production system. Employing such an offline learning approach has many benefits compared to an online one, but it…

Machine Learning · Computer Science 2020-05-22 Rolf Jagerman , Maarten de Rijke

Smishing, which aims to illicitly obtain personal information from unsuspecting victims, holds significance due to its negative impacts on our society. In prior studies, as a tool to counteract smishing, machine learning (ML) has been…

Social and Information Networks · Computer Science 2024-11-07 Ho Sung Shim , Hyoungjun Park , Kyuhan Lee , Jang-Sun Park , Seonhye Kang

Large Language Models (LLMs) are vulnerable to prompt injection attacks, and several defenses have recently been proposed, often claiming to mitigate these attacks successfully. However, we argue that existing studies lack a principled…

Cryptography and Security · Computer Science 2025-05-27 Yuqi Jia , Zedian Shao , Yupei Liu , Jinyuan Jia , Dawn Song , Neil Zhenqiang Gong

Personality manipulation in large language models (LLMs) is increasingly applied in customer service and agentic scenarios, yet its mechanisms and trade-offs remain unclear. We present a systematic study of personality control using the Big…

Computation and Language · Computer Science 2025-09-08 Gunmay Handa , Zekun Wu , Adriano Koshiyama , Philip Treleaven

Activity classification has observed great success recently. The performance on small dataset is almost saturated and people are moving towards larger datasets. What leads to the performance gain on the model and what the model has learnt?…

Computer Vision and Pattern Recognition · Computer Science 2019-12-16 Jialing Lyu , Weichao Qiu , Xinyue Wei , Yi Zhang , Alan Yuille , Zheng-Jun Zha

Deep neural networks have demonstrated cutting edge performance on various tasks including classification. However, it is well known that adversarially designed imperceptible perturbation of the input can mislead advanced classifiers. In…

Machine Learning · Computer Science 2020-01-07 Mehdi Jafarnia-Jahromi , Tasmin Chowdhury , Hsin-Tai Wu , Sayandev Mukherjee

Prompt injection attacks are a critical security vulnerability in large language models (LLMs), allowing attackers to hijack model behavior by injecting malicious instructions within the input context. Recent defense mechanisms have…

Artificial Intelligence · Computer Science 2026-03-10 Sanjay Kariyappa , G. Edward Suh

Large Language Models (LLMs) have transformed natural language processing and hold growing promise for advancing science, healthcare, and decision-making. Yet their training paradigms remain dominated by affirmation-based inference, akin to…

Artificial Intelligence · Computer Science 2025-12-05 Peter B. Walker , Hannah Davidson , Aiden Foster , Matthew Lienert , Thomas Pardue , Dale Russell

The output tendencies of Pre-trained Language Models (PLM) vary markedly before and after Fine-Tuning (FT) due to the updates to the model parameters. These divergences in output tendencies result in a gap in the social biases of PLMs. For…

Computation and Language · Computer Science 2024-01-17 Masahiro Kaneko , Danushka Bollegala , Timothy Baldwin

Deep learning models have shown impressive performance across a spectrum of computer vision applications including medical diagnosis and autonomous driving. One of the major concerns that these models face is their susceptibility to…

Machine Learning · Computer Science 2020-04-22 Vivek B. S. , R. Venkatesh Babu

An increasing number of NLP applications interact with large language models (LLMs) through black-box APIs, making prompt engineering critical for controlling model outputs. While recent Automatic Prompt Optimization (APO) methods…

Machine Learning · Computer Science 2025-07-15 MohammadReza Davari , Utkarsh Garg , Weixin Cai , Eugene Belilovsky

Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the predictions…

Machine Learning · Computer Science 2017-11-28 Andrew Slavin Ross , Finale Doshi-Velez

This paper investigates prior prompt engineering (pPE) in the context of reinforcement fine-tuning (RFT), where language models (LMs) are incentivized to exhibit behaviors that maximize performance through reward signals. While existing RFT…

Computation and Language · Computer Science 2025-09-11 Pittawat Taveekitworachai , Potsawee Manakul , Sarana Nutanong , Kunat Pipatanakul