Search Results for author:
Found 23 papers, 9 papers with code
Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss
In addition, by theoretically analyzing the nature of Lipschitz neural networks, we introduce a new loss function that employs an annealing mechanism to increase margin for most data points.
Jailbreaking with Universal Multi-Prompts
Large language models (LLMs) have seen rapid development in recent years, revolutionizing various applications and significantly enhancing convenience and productivity.
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
In this paper, we address the question: How can we improve downstream task performance while preserving safety in LLMs without relying on additional safety data?
Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
Model Inversion (MI) attacks pose a significant threat to the privacy of Deep Neural Networks by recovering training data distribution from well-trained models.
Adversarial Robustness Overestimation and Instability in TRADES
This paper examines the phenomenon of probabilistic robustness overestimation in TRADES, a prominent adversarial training method.
Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation
The robust self-training (RST) framework has emerged as a prominent approach for semi-supervised adversarial training.
Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition
Synthetic data is widely used in speech recognition due to the availability of text-to-speech models, which facilitate adapting models to previously unseen text domains.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models
Recently, researchers have made considerable improvements in dialogue systems with the progress of large language models (LLMs) such as ChatGPT and GPT-4.
Annealing Self-Distillation Rectification Improves Adversarial Training
To address this issue and enhance adversarial robustness, we analyze the characteristics of robust models and identify that robust models tend to produce smoother and well-calibrated outputs.
Position Matters! Empirical Study of Order Effect in Knowledge-grounded Dialogue
With the power of large pretrained language models, various research works have integrated knowledge into dialogue systems.
Towards Large Certified Radius in Randomized Smoothing using Quasiconcave Optimization
This observation leads to an efficient and effective input-specific randomized smoothing algorithm.
Fair Robust Active Learning by Joint Inconsistency
Fairness and robustness play vital roles in trustworthy machine learning.
Enhancing Targeted Attack Transferability via Diversified Weight Pruning
In this work, we propose Diversified Weight Pruning (DWP), a novel model augmentation technique for generating transferable targeted attacks.
Learning to Generate Prompts for Dialogue Generation through Reinforcement Learning
Much literature has shown that prompt-based learning is an efficient method to make use of the large pre-trained language model.
UnMask: Adversarial Detection and Defense Through Robust Feature Alignment
UnMask detects such attacks and defends the model by rectifying the misclassification, re-classifying the image based on its robust features.
Talk Proposal: Towards the Realistic Evaluation of Evasion Attacks using CARLA
In this talk we describe our content-preserving attack on object detectors, ShapeShifter, and demonstrate how to evaluate this threat in realistic scenarios.
The Efficacy of SHIELD under Different Threat Models
To evaluate the robustness of the defense against an adaptive attacker, we consider the targeted-attack success rate of the Projected Gradient Descent (PGD) attack, which is a strong gradient-based adversarial attack proposed in adversarial machine learning research.
ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio
Adversarial machine learning research has recently demonstrated the feasibility to confuse automatic speech recognition (ASR) models by introducing acoustically imperceptible perturbations to audio samples.
ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector
Given the ability to directly manipulate image pixels in the digital input space, an adversary can easily generate imperceptible perturbations to fool a Deep Neural Network (DNN) image classifier, as demonstrated in prior work.
Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression
The rapidly growing body of research in adversarial machine learning has demonstrated that deep neural networks (DNNs) are highly vulnerable to adversarially generated images.
Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
Deep neural networks (DNNs) have achieved great success in solving a variety of machine learning (ML) problems, especially in the domain of image recognition.
Communication Efficient Distributed Agnostic Boosting
We consider the problem of learning from distributed data in the agnostic setting, i. e., in the presence of arbitrary forms of noise.
