TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks

• URL: http://arxiv.org/abs/2506.10722v1
• Date: Thu, 12 Jun 2025 14:12:15 GMT
• Title: TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
• Abstract summary: Topological Evolution Dynamics (TED) has emerged as a powerful tool for detecting backdoor attacks in Deep Neural Networks (DNNs)<n>TED can be vulnerable to backdoor attacks that adaptively distort topological representation distributions across network layers.<n>We propose TED-LaST, a novel defense strategy that enhances TED's robustness against adaptive attacks.
• Score: 9.664747681518465
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep Neural Networks (DNNs) are vulnerable to backdoor attacks, where attackers implant hidden triggers during training to maliciously control model behavior. Topological Evolution Dynamics (TED) has recently emerged as a powerful tool for detecting backdoor attacks in DNNs. However, TED can be vulnerable to backdoor attacks that adaptively distort topological representation distributions across network layers. To address this limitation, we propose TED-LaST (Topological Evolution Dynamics against Laundry, Slow release, and Target mapping attack strategies), a novel defense strategy that enhances TED's robustness against adaptive attacks. TED-LaST introduces two key innovations: label-supervised dynamics tracking and adaptive layer emphasis. These enhancements enable the identification of stealthy threats that evade traditional TED-based defenses, even in cases of inseparability in topological space and subtle topological perturbations. We review and classify data poisoning tricks in state-of-the-art adaptive attacks and propose enhanced adaptive attack with target mapping, which can dynamically shift malicious tasks and fully leverage the stealthiness that adaptive attacks possess. Our comprehensive experiments on multiple datasets (CIFAR-10, GTSRB, and ImageNet100) and model architectures (ResNet20, ResNet101) show that TED-LaST effectively counteracts sophisticated backdoors like Adap-Blend, Adapt-Patch, and the proposed enhanced adaptive attack. TED-LaST sets a new benchmark for robust backdoor detection, substantially enhancing DNN security against evolving threats.

Related papers

• Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attack [1.2373172839910807]
  This work discusses the vulnerability of current speech triggers to detection by deep neural network defenders and introduces the Timbre Leakage Attack (TLA)<n>TLA disseminates timbre information at the frame level within the deep self-supervised features, producing poisoned samples that appear natural to human perception.
  arXiv  Detail & Related papers  (2026-07-02T04:51:27Z)
• Semantically-Equivalent Transformations-Based Backdoor Attacks against Neural Code Models: Characterization and Mitigation [13.36343806244795]
  We introduce a new kind of backdoor attacks, dubbed Semantically-Equivalent Transformation (SET)-based backdoor attacks.<n>We show that SET-based attacks achieve high success rates (often >90%) while preserving model utility.<n>The attack proves highly stealthy, evading state-of-the-art defenses with detection rates on average over 25.13% lower than injection-based counterparts.
  arXiv  Detail & Related papers  (2025-12-22T09:54:52Z)
• TED++: Submanifold-Aware Backdoor Detection via Layerwise Tubular-Neighbourhood Screening [62.75464575596457]
  TED++ is a submanifold-aware framework that effectively detects subtle backdoors.<n>It captures how faithfully an admissible input remains on the evolving class submanifolds.<n>It achieves near-perfect detection, achieving gains of up to 14% in AUROC over the next-best method.
  arXiv  Detail & Related papers  (2025-10-16T04:51:25Z)
• DOPA: Stealthy and Generalizable Backdoor Attacks from a Single Client under Challenging Federated Constraints [2.139012072214621]
  Federated Learning (FL) is increasingly adopted for privacy-preserving collaborative training, but its decentralized nature makes it susceptible to backdoor attacks.<n>Existing attack methods, however, often rely on idealized assumptions and fail to remain effective under real-world constraints.<n>We propose DOPA, a novel framework that simulates heterogeneous local training dynamics and seeks consensus across divergent optimization trajectories to craft universally effective and stealthy backdoor triggers.
  arXiv  Detail & Related papers  (2025-08-20T08:39:12Z)
• TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models [67.06525001375722]
  TrojanTO is the first action-level backdoor attack against TO models.<n>It implants backdoor attacks across diverse tasks and attack objectives with a low attack budget.<n>TrojanTO exhibits broad applicability to DT, GDT, and DC.
  arXiv  Detail & Related papers  (2025-06-15T11:27:49Z)
• Co-Evolutionary Defence of Active Directory Attack Graphs via GNN-Approximated Dynamic Programming [3.8352746394815815]
  We model attacker-defender interactions in Active Directory as a Stackelberg game between an adaptive attacker and a proactive defender.<n>We propose a co-evolutionary defense framework that combines Graph Neural Network Approximated Dynamic Programming (GNNDP) to model attacker strategies.<n>Our framework refines attacker and defender policies to improve generalization and prevent premature convergence.
  arXiv  Detail & Related papers  (2025-05-16T21:37:50Z)
• ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models [55.93380086403591]
  Generative large language models are vulnerable to backdoor attacks.<n>$textitELBA-Bench$ allows attackers to inject backdoor through parameter efficient fine-tuning.<n>$textitELBA-Bench$ provides over 1300 experiments.
  arXiv  Detail & Related papers  (2025-02-22T12:55:28Z)
• BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning [85.2564206440109]
  This paper reveals the threats in this practical scenario that backdoor attacks can remain effective even after defenses. We introduce the emphtoolns attack, which is resistant to backdoor detection and model fine-tuning defenses.
  arXiv  Detail & Related papers  (2023-11-20T02:21:49Z)
• Tabdoor: Backdoor Vulnerabilities in Transformer-based Neural Networks for Tabular Data [14.415796842972563]
  We present a comprehensive analysis of backdoor attacks on tabular data using Deep Neural Networks (DNNs) We propose a novel approach for trigger construction: an in-bounds attack, which provides excellent attack performance while maintaining stealthiness. Our results demonstrate up to 100% attack success rate with negligible clean accuracy drop.
  arXiv  Detail & Related papers  (2023-11-13T18:39:44Z)
• Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs [40.01361505644007]
  We propose T-SPEAR, a simple and effective adversarial attack method for link prediction on continuous-time dynamic graphs. We show that T-SPEAR significantly degrades the victim model's performance on link prediction tasks. Our attacks are transferable to other TGNNs, which differ from the victim model assumed by the attacker.
  arXiv  Detail & Related papers  (2023-08-21T15:09:51Z)
• Backdoor Attack with Sparse and Invisible Trigger [57.41876708712008]
  Deep neural networks (DNNs) are vulnerable to backdoor attacks. backdoor attack is an emerging yet threatening training-phase threat. We propose a sparse and invisible backdoor attack (SIBA)
  arXiv  Detail & Related papers  (2023-05-11T10:05:57Z)
• RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN [28.94653593443991]
  Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models. In this paper, we propose to study and develop Robust and Imperceptible Backdoor Attack against Compact DNN models (RIBAC)
  arXiv  Detail & Related papers  (2022-08-22T21:27:09Z)
• The Feasibility and Inevitability of Stealth Attacks [63.14766152741211]
  We study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence systems. In contrast to adversarial data modification, the attack mechanism we consider here involves alterations to the AI system itself.
  arXiv  Detail & Related papers  (2021-06-26T10:50:07Z)
• Policy Smoothing for Provably Robust Reinforcement Learning [109.90239627115336]
  We study the provable robustness of reinforcement learning against norm-bounded adversarial perturbations of the inputs. We generate certificates that guarantee that the total reward obtained by the smoothed policy will not fall below a certain threshold under a norm-bounded adversarial of perturbation the input.
  arXiv  Detail & Related papers  (2021-06-21T21:42:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.