Search Results for author:
Found 14 papers, 9 papers with code
UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
While existing works have proposed various methods to mitigate backdoor effects in poisoned models, they tend to be less effective against recent advanced attacks.
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
Backdoor attack poses a significant security threat to Deep Learning applications.
Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia
Large Language Models (LLMs) have become prevalent across diverse sectors, transforming human life with their extraordinary reasoning and comprehension abilities.
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
Diffusion models (DM) have become state-of-the-art generative models because of their capability to generate high-quality images from noises without adversarial training.
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks.
MEDIC: Remove Model Backdoors via Importance Driven Cloning
It trains the clone model from scratch on a very small subset of samples and aims to minimize a cloning loss that denotes the differences between the activations of important neurons across the two models.
Backdoor Vulnerabilities in Normally Trained Deep Learning Models
We leverage 20 different types of injected backdoor attacks in the literature as the guidance and study their correspondences in normally trained models, which we call natural backdoor vulnerabilities.
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
In this work, we theoretically analyze the connection among cross-entropy loss, attack success rate, and clean accuracy in this setting.
Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer
Existing defenses are mainly built upon the observation that the backdoor trigger is usually of small size or affects the activation of only a few neurons.
DECK: Model Hardening for Defending Pervasive Backdoors
As such, using the samples derived from our attack in adversarial training can harden a model against these backdoor vulnerabilities.
Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense
We develop a novel optimization method for NLPbackdoor inversion.
Better Trigger Inversion Optimization in Backdoor Scanning
A popular trigger inversion method is by optimization.
Backdoor Attack through Frequency Domain
We also evaluate FTROJAN against state-of-the-art defenses as well as several adaptive defenses that are designed on the frequency domain.
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
By iteratively and stochastically selecting the most promising labels for optimization with the guidance of an objective function, we substantially reduce the complexity, allowing to handle models with many classes.
