228 citations · 270 across the 10 of their papers we have counts for
10 papers
Latent Traits and Cross-Task Transfer: Deconstructing Dataset Interactions in LLM Fine-tuning
Shambhavi Krishna, Atharva Naik, Chaitali Agarwal +3
Large language models are increasingly deployed across diverse applications. This often includes tasks LLMs have not encountered during training. This implies that enumerating and…
Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Mrinank Sharma, Meg Tong, Jesse Mu +40
Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes…
Towards Generating Informative Textual Description for Neurons in Language Models
Shrayani Mondal, Rishabh Garodia, Arbaaz Qureshi +2
Recent developments in transformer-based language models have allowed them to capture a wide variety of world knowledge that can be adapted to downstream tasks with limited resourc…
URET: Universal Robustness Evaluation Toolkit (for Evasion)
Kevin Eykholt, Taesung Lee, Douglas Schales +3
Machine learning models are known to be vulnerable to adversarial evasion attacks as illustrated by image classification models. Thoroughly understanding such attacks is critical i…
Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models
Myles Foley, Ambrish Rawat, Taesung Lee +3
The wide applicability and adaptability of generative large language models (LLMs) has enabled their rapid adoption. While the pre-trained models can perform many tasks, such model…
Robustness of Explanation Methods for NLP Models
Shriya Atmakuri, Tejas Chheda, Dinesh Kandula +3
Explanation methods have emerged as an important tool to highlight the features responsible for the predictions of neural networks. There is mounting evidence that many explanation…
Adaptive Verifiable Training Using Pairwise Class Similarity
Shiqi Wang, Kevin Eykholt, Taesung Lee +2
Verifiable training has shown success in creating neural networks that are provably robust to a given amount of noise. However, despite only enforcing a single robustness criterion…
Backdoor Smoothing: Demystifying Backdoor Attacks on Deep Neural Networks
Kathrin Grosse, Taesung Lee, Battista Biggio +3
Backdoor attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require poisoning the training…
Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
Bryant Chen, Wilka Carvalho, Nathalie Baracaldo +5
While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing…
Defending Against Machine Learning Model Stealing Attacks Using Deceptive Perturbations
Taesung Lee, Benjamin Edwards, Ian Molloy +1
Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs. To protect against these attacks, it has been p…