Smoothllm: Defending large language models against jailbreaking attacks
Despite efforts to align large language models (LLMs) with human values, widely-used
LLMs such as GPT, Llama, Claude, and PaLM are susceptible to jailbreaking attacks …
LLMs such as GPT, Llama, Claude, and PaLM are susceptible to jailbreaking attacks …
Random features for kernel approximation: A survey on algorithms, theory, and beyond
The class of random features is one of the most popular techniques to speed up kernel
methods in large-scale problems. Related works have been recognized by the NeurIPS Test …
methods in large-scale problems. Related works have been recognized by the NeurIPS Test …
On the tradeoff between robustness and fairness
Abstract Interestingly, recent experimental results [2, 26, 22] have identified a robust fairness
phenomenon in adversarial training (AT), namely that a robust model well-trained by AT …
phenomenon in adversarial training (AT), namely that a robust model well-trained by AT …
Feature purification: How adversarial training performs robust deep learning
Z Allen-Zhu, Y Li - 2021 IEEE 62nd Annual Symposium on …, 2022 - ieeexplore.ieee.org
Despite the empirical success of using adversarial training to defend deep learning models
against adversarial perturbations, so far, it still remains rather unclear what the principles are …
against adversarial perturbations, so far, it still remains rather unclear what the principles are …
A model of double descent for high-dimensional binary linear classification
We consider a model for logistic regression where only a subset of features of size is used
for training a linear classifier over training samples. The classifier is obtained by running …
for training a linear classifier over training samples. The classifier is obtained by running …
Enhanced accuracy and robustness via multi-teacher adversarial distillation
Adversarial training is an effective approach for improving the robustness of deep neural
networks against adversarial attacks. Although bringing reliable robustness, adversarial …
networks against adversarial attacks. Although bringing reliable robustness, adversarial …
The Triangular Trade-off between Robustness, Accuracy and Fairness in Deep Neural Networks: A Survey
With the rapid development of deep learning, AI systems are being used more in complex
and important domains and necessitates the simultaneous fulfillment of multiple constraints …
and important domains and necessitates the simultaneous fulfillment of multiple constraints …
Improving generalization of adversarial training via robust critical fine-tuning
Deep neural networks are susceptible to adversarial examples, posing a significant security
risk in critical applications. Adversarial Training (AT) is a well-established technique to …
risk in critical applications. Adversarial Training (AT) is a well-established technique to …
Stability analysis and generalization bounds of adversarial training
In adversarial machine learning, deep neural networks can fit the adversarial examples on
the training dataset but have poor generalization ability on the test set. This phenomenon is …
the training dataset but have poor generalization ability on the test set. This phenomenon is …
Randomized adversarial training via taylor expansion
In recent years, there has been an explosion of research into developing more robust deep
neural networks against adversarial examples. Adversarial training appears as one of the …
neural networks against adversarial examples. Adversarial training appears as one of the …