1 citations · 1 across the 8 of their papers we have counts for
9 papers
Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
Vanshaj Khattar, Md Rafi ur Rashid, Moumita Choudhury +4
Test-time training (TTT) has recently emerged as a promising method to improve the reasoning abilities of large language models (LLMs), in which the model directly learns from test…
From Insight to Exploit: Leveraging LLM Collaboration for Adaptive Adversarial Text Generation
Najrin Sultana, Md Rafi Ur Rashid, Kang Gu +1
LLMs can provide substantial zero-shot performance on diverse tasks using a simple task prompt, eliminating the need for training or fine-tuning. However, when applying these model…
Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models
Md Rafi Ur Rashid, Vishnu Asutosh Dasu, Ye Wang +2
Large Language Models (LLMs) exhibit impressive capabilities, but remain susceptible to a growing spectrum of safety risks, including jailbreaks, toxic content, hallucinations, and…
Attention Pruning: Automated Fairness Repair of Language Models via Surrogate Simulated Annealing
Vishnu Asutosh Dasu, Md Rafi ur Rashid, Vipul Gupta +2
This paper explores pruning attention heads as a post-processing bias mitigation method for large language models (LLMs). Modern AI systems such as LLMs are expanding into sensitiv…
Smoothed Embeddings for Robust Language Models
Ryo Hase, Md Rafi Ur Rashid, Ashley Lewis +4
Improving the safety and reliability of large language models (LLMs) is a crucial aspect of realizing trustworthy AI systems. Although alignment methods aim to suppress harmful con…
SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains
Bijoy Ahmed Saiem, MD Sadik Hossain Shanto, Rakib Ahsan +1
As the integration of the Large Language Models (LLMs) into various applications increases, so does their susceptibility to misuse, raising significant security concerns. Numerous…
Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage
Md Rafi Ur Rashid, Jing Liu, Toshiaki Koike-Akino +2
Fine-tuning large language models on private data for downstream applications poses significant privacy risks in potentially exposing sensitive information. Several popular communi…
Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models
Kang Gu, Md Rafi Ur Rashid, Najrin Sultana +1
With the rapid development of Large Language Models (LLMs), we have witnessed intense competition among the major LLM products like ChatGPT, LLaMa, and Gemini. However, various iss…
Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
Md Rafi Ur Rashid, Vishnu Asutosh Dasu, Kang Gu +2
Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis. These a…