Adversarial ML

The paper proposes SemBugger, a polymorphic backdoor attack that uses intensity-based poisoning to achieve diverse malicious outcomes in Semantic Communication (SC) systems, alongside a provable defen…

This paper surveys the security vulnerabilities of Variational Quantum Circuits (VQCs) to backdoor attacks, detailing various attack mechanisms and analyzing current detection and defense strategies.

This paper evaluates and improves defenses against poisoning and backdoor attacks in federated learning for intrusion detection systems.

ProtoGuard-SL introduces a server-side defense that enhances vertical split learning robustness against backdoor attacks by enforcing class-conditional consistency in the embedding space.

This paper challenges the assumption that differential privacy enhances the robustness of federated learning against backdoor attacks and proposes a novel attack called RING.

The paper introduces Checkerboard, a novel, learning-free clean-label backdoor attack that efficiently poisons training data to compromise model integrity with minimal poisoning budget.

This paper proposes a general framework for certifying robustness against data poisoning attacks in machine learning systems.

The paper introduces Dummy-Aware Weighted Attack (DAWA), a novel evaluation method that significantly reduces the reported robustness of Dummy Classes-based defenses by simultaneously targeting both t…

This paper demonstrates that Concept Bottleneck Models (CBMs), despite their interpretability, are highly vulnerable to targeted adversarial attacks that manipulate semantic concepts, and proposes SPE…

The paper introduces SORA, an adaptive adversarial training method that dynamically adjusts perturbation sizes to prevent Catastrophic Overfitting, achieving state-of-the-art robustness and clean accu…

This paper proposes a training-free defense against multi-trigger backdoor attacks in machine learning models.

The paper proposes BiRD, a bidirectional ranking defense mechanism that enhances the robustness of Retrieval-Augmented Generation (RAG) against adversarial attacks by analyzing the alignment between f…

The paper proposes Cluster Segregation Concealment (CSC), a novel defense that identifies and neutralizes backdoor triggers by relabeling poisoned samples to a virtual class, achieving near-zero attac…

This paper proposes DRL-CLBA, a novel clean label backdoor attack for speech classification using Deep Deterministic Policy Gradient (DDPG) reinforcement learning and deep audio steganography.

The paper proposes a novel cross-modal backdoor attack that exploits the vulnerability of lightweight connectors in multimodal LLMs, demonstrating high attack success rates across different modalities…

This paper introduces the first backdoor attack specifically targeting pipeline parallelism in decentralized post-training, demonstrating that a limited adversary controlling an intermediate stage can…

This paper introduces the first backdoor attacks against VLM-based scanpath prediction, demonstrating variable-output attacks that evade detection and survive deployment on edge devices.

This paper investigates a novel physical backdoor attack against Deep Automatic Modulation Classifiers (AMC) in wireless communications, demonstrating that an adversary using Explainable AI (XAI) can…

This paper investigates the vulnerability of machine learning-based fault detection and localization systems in Cyber-Physical Systems (CPS) to backdoor attacks, demonstrating that such attacks are su…

The paper introduces PromptFuzz-SC, a novel semantic-character dual-space mutation framework, demonstrating that combining both semantic and character-level attacks significantly improves the robustne…