paper-with-me

홈 › Papers

Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off

2021-09-29 · ICLR 2022 4 · Rahul Rade, Seyed-Mohsen Moosavi-Dezfooli

While adversarial training has become the de facto approach for training robust classifiers, it leads to a drop in accuracy. This has led to prior works postulating that accuracy is inherently at odds with robustness. Yet, the phenomenon remains inexplicable. In this paper, we closely examine the changes induced in the decision boundary of a deep network during adversarial training. We find that adversarial training leads to unwarranted increase in the margin along certain adversarial directions, thereby hurting accuracy. Motivated by this observation, we present a novel algorithm, called Helper-based Adversarial Training (HAT), to reduce this effect by incorporating additional wrongly labelled examples during training. Our proposed method provides a notable improvement in accuracy without compromising robustness. It achieves a better trade-off between accuracy and robustness in comparison to existing defenses.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off

2021-06-18 · ICMLW 2021 6 · Rahul Rade, Seyed-Mohsen Moosavi-Dezfooli

While adversarial training has become the de facto approach for training robust classifiers, it leads to a drop in accuracy. This has led to prior works postulating that accuracy is inherently at odds with robustness. Ye…

Adversarial DefenseAdversarial RobustnessRobust classification

Reducing Class-Wise Performance Disparity via Margin Regularization

2026-01-30 · Beier Zhu, Kesen Zhao, Jiequan Cui, Qianru Sun 외 arxiv

Deep neural networks often exhibit substantial disparities in class-wise accuracy, even when trained on class-balanced data, posing concerns for reliable deployment. While prior efforts have explored empirical remedies, …

AMaPO: Adaptive Margin-attached Preference Optimization for Language Model Alignment

2025-11-12 · Ruibo Deng, Duanyu Feng, Wenqiang Lei arxiv

Offline preference optimization offers a simpler and more stable alternative to RLHF for aligning language models. However, their effectiveness is critically dependent on ranking accuracy, a metric where further gains ar…

VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference

2021-02-08 · Steve Dai, Rangharajan Venkatesan, Haoxing Ren, Brian Zimmer 외

Quantization enables efficient acceleration of deep neural networks by reducing model memory footprint and exploiting low-cost integer math hardware units. Quantization maps floating-point weights and activations in a tr…

MathQuantization

Not All Tokens Are What You Need In Thinking

2025-05-23 · Hang Yuan, Bin Yu, Haotian Li, Shijun Yang 외

Modern reasoning models, such as OpenAI's o1 and DeepSeek-R1, exhibit impressive problem-solving capabilities but suffer from critical inefficiencies: high inference latency, excessive computational resource consumption,…

AllToken Reduction