:: Library Catalog

Copertina

Salvato in:

Dettagli Bibliografici
Autori principali:	Peng, Jie, Yang, Hongwei, Zhao, Jing, Dong, Hengji, He, Hui, Zhang, Weizhe, He, Haoyu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	https://arxiv.org/abs/2506.07467
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Preserving Continuous Symmetry in Discrete Spaces: Geometric-Aware Quantization for SO(3)-Equivariant GNNs
di: Zhou, Haoyu, et al.
Pubblicazione: (2026)

Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
di: Lin, Weilin, et al.
Pubblicazione: (2024)

Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models
di: He, Jiaming, et al.
Pubblicazione: (2024)

Membership Inference Attack with Partial Features
di: Wang, Xurun, et al.
Pubblicazione: (2025)

Instruction Backdoor Attacks Against Customized LLMs
di: Zhang, Rui, et al.
Pubblicazione: (2024)

Understanding Mode Connectivity via Parameter Space Symmetry
di: Zhao, Bo, et al.
Pubblicazione: (2025)

Poisoning with A Pill: Circumventing Detection in Federated Learning
di: Guo, Hanxi, et al.
Pubblicazione: (2024)

Exploit Gradient Skewness to Circumvent Byzantine Defenses for Federated Learning
di: Liu, Yuchen, et al.
Pubblicazione: (2025)

Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
di: Wang, Yifei, et al.
Pubblicazione: (2026)

Magnitude-based Neuron Pruning for Backdoor Defens
di: Li, Nan, et al.
Pubblicazione: (2024)

Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs
di: Wang, Jing, et al.
Pubblicazione: (2026)

Latent Space Symmetry Discovery
di: Yang, Jianke, et al.
Pubblicazione: (2023)

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval
di: Srivastava, Saksham Sahai, et al.
Pubblicazione: (2025)

State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space
di: Guo, Ji, et al.
Pubblicazione: (2026)

Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias
di: Wu, Shangxi, et al.
Pubblicazione: (2023)

Authority Backdoor: A Certifiable Backdoor Mechanism for Authoring DNNs
di: Yang, Han, et al.
Pubblicazione: (2025)

A Semantic and Clean-label Backdoor Attack against Graph Convolutional Networks
di: Dai, Jiazhu, et al.
Pubblicazione: (2025)

FLAIN: Mitigating Backdoor Attacks in Federated Learning via Flipping Weight Updates of Low-Activation Input Neurons
di: Ding, Binbin, et al.
Pubblicazione: (2024)

InkDrop: Invisible Backdoor Attacks Against Dataset Condensation
di: Yang, He, et al.
Pubblicazione: (2026)

Effective Sparsity: A Unified Framework via Normalized Entropy and the Effective Number of Nonzeros
di: He, Haoyu, et al.
Pubblicazione: (2026)

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks
di: He, Bowei, et al.
Pubblicazione: (2025)

Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
di: Zheng, Xiaosen, et al.
Pubblicazione: (2024)

Sample Weight Averaging for Stable Prediction
di: Yu, Han, et al.
Pubblicazione: (2025)

Turn-Based Structural Triggers: Prompt-Free Backdoors in Multi-Turn LLMs
di: Lu, Yiyang, et al.
Pubblicazione: (2026)

ArcGen: Generalizing Neural Backdoor Detection Across Diverse Architectures
di: Yang, Zhonghao, et al.
Pubblicazione: (2025)

Symmetry in Neural Network Parameter Spaces
di: Zhao, Bo, et al.
Pubblicazione: (2025)

Your Compiler is Backdooring Your Model: Understanding and Exploiting Compilation Inconsistency Vulnerabilities in Deep Learning Compilers
di: Chen, Simin, et al.
Pubblicazione: (2025)

Improved Generalization of Weight Space Networks via Augmentations
di: Shamsian, Aviv, et al.
Pubblicazione: (2024)

Weight Space Representation Learning via Neural Field Adaptation
di: Yang, Zhuoqian, et al.
Pubblicazione: (2025)

A Unified Fractional Regularization Framework for Sparse Recovery
di: Zhao, Yinhao, et al.
Pubblicazione: (2026)

Vertical Federated Unlearning via Backdoor Certification
di: Han, Mengde, et al.
Pubblicazione: (2024)

Concept Arithmetics for Circumventing Concept Inhibition in Diffusion Models
di: Petsiuk, Vitali, et al.
Pubblicazione: (2024)

Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation
di: Lin, Weilin, et al.
Pubblicazione: (2024)

Beyond Uniform Deletion: A Data Value-Weighted Framework for Certified Machine Unlearning
di: He, Lisong, et al.
Pubblicazione: (2025)

FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
di: Yan, Xinhai, et al.
Pubblicazione: (2025)

FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation
di: Bao, Guangsheng, et al.
Pubblicazione: (2026)

OCGEC: One-class Graph Embedding Classification for DNN Backdoor Detection
di: Jiang, Haoyu, et al.
Pubblicazione: (2023)

Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability
di: Wang, Hao, et al.
Pubblicazione: (2024)

Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization
di: Yang, Guangmingmei, et al.
Pubblicazione: (2025)

Fast and Lightweight Backdoor Detection via Head Random Probing
di: Yu, Yinbo, et al.
Pubblicazione: (2026)