FPR manipulation attack perturbs benign MQTT packets to flip labels to attacks in NIDS with 80-100% success, increasing SOC delays without gradient-based methods.
Fast is better than free: Revisiting adversarial training
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A test-time adaptation framework anchors adversarial training to a non-robust teacher's predictions, yielding more stable optimization and better robustness-accuracy trade-offs than standard self-consistency methods.
The FastAT Benchmark standardizes evaluation of over twenty fast adversarial training methods under unified conditions, showing that well-designed single-step approaches can match or exceed PGD-AT robustness at lower training cost on CIFAR-10, CIFAR-100, and Tiny-ImageNet.
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
GF-Score decomposes certified robustness into per-class profiles, adds fairness metrics like disparity index and Gini coefficient, and uses self-calibration on clean accuracy to avoid adversarial attacks.
Random quantum circuits used as adversarial training data reduce successful attack rates on QML models for CIFAR-10 from 89.8% to 68.45% and for CINIC-10 from 94.23% to 78.68%.
Compression acts as an adversarial amplifier by reducing the decision space of image classifiers, making attacks in compressed representations substantially more effective than pixel-space attacks under the same perturbation budget.
SmoothLLM mitigates jailbreaking attacks on LLMs by randomly perturbing multiple copies of a prompt at the character level and aggregating the outputs to detect adversarial inputs.
An adaptive l^p norm control in FGSM adversarial training, guided by participation ratio and entropy of gradients, mitigates catastrophic overfitting without noise or regularization.
citing papers explorer
-
Uncovering and Understanding FPR Manipulation Attack in Industrial IoT Networks
FPR manipulation attack perturbs benign MQTT packets to flip labels to attacks in NIDS with 80-100% success, increasing SOC delays without gradient-based methods.
-
Learning Robustness at Test-Time from a Non-Robust Teacher
A test-time adaptation framework anchors adversarial training to a non-robust teacher's predictions, yielding more stable optimization and better robustness-accuracy trade-offs than standard self-consistency methods.
-
FastAT Benchmark: A Comprehensive Framework for Fair Evaluation of Fast Adversarial Training Methods
The FastAT Benchmark standardizes evaluation of over twenty fast adversarial training methods under unified conditions, showing that well-designed single-step approaches can match or exceed PGD-AT robustness at lower training cost on CIFAR-10, CIFAR-100, and Tiny-ImageNet.
-
Representation-Guided Parameter-Efficient LLM Unlearning
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
-
GF-Score: Certified Class-Conditional Robustness Evaluation with Fairness Guarantees
GF-Score decomposes certified robustness into per-class profiles, adds fairness metrics like disparity index and Gini coefficient, and uses self-calibration on clean accuracy to avoid adversarial attacks.
-
Quantum Patches: Enhancing Robustness of Quantum Machine Learning Models
Random quantum circuits used as adversarial training data reduce successful attack rates on QML models for CIFAR-10 from 89.8% to 68.45% and for CINIC-10 from 94.23% to 78.68%.
-
Compression as an Adversarial Amplifier Through Decision Space Reduction
Compression acts as an adversarial amplifier by reducing the decision space of image classifiers, making attacks in compressed representations substantially more effective than pixel-space attacks under the same perturbation budget.
-
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
SmoothLLM mitigates jailbreaking attacks on LLMs by randomly perturbing multiple copies of a prompt at the character level and aggregating the outputs to detect adversarial inputs.
-
Catastrophic Overfitting, Entropy Gap and Participation Ratio: A Noiseless $l^p$ Norm Solution for Fast Adversarial Training
An adaptive l^p norm control in FGSM adversarial training, guided by participation ratio and entropy of gradients, mitigates catastrophic overfitting without noise or regularization.