Backdoor Detection

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 34

All topics

Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
May 8, 2026Fan Yang, Binyan Xu, Di Tang +1Graph Neural Networks Backdoor Attacks
The Chinese University of Hong Kong · Sun Yat-Sen University
Activation Differences Reveal Backdoors: A Comparison of SAE Architectures
May 8, 2026Sachin KumarLLM Backdoor Attacks LLM Interpretability
LexisNexis* · Raleigh, USA
BehaviorGuard: Online Backdoor Defense for Deep Reinforcement Learning
May 7, 2026Yinbo Yu, Xueyu Yin, Jiadai Wang +4Backdoor Attacks Backdoor Detection
College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics · School of Cybersecurity, Northwestern Polytechnical University · School of Computer Science and Technology, Harbin Institute of Technology +1
Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning
Mar 17, 2026Shenao Yan, Shan Jin, Shimaa Ahmed +4LLM Auditing Backdoor Detection
University of Connecticut · Visa Research

May 8, 2026, cs.LGJ/K move · Enter open · S save

Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors

Fan Yang, Binyan Xu, Di Tang, Kehuan Zhang

The Chinese University of Hong Kong · Sun Yat-Sen University

Graph Neural Networks Backdoor Attacks Backdoor Detection Backdoor Defense

Open paper AskPDF arXiv

GNNs have become a standard tool for learning on relational data, yet they remain highly vulnerable to backdoor attacks. Prior defenses often depend on inspecting specific subgraph patterns or node features, and thus can be circumvented by adaptive attackers. We propose PRAETORIAN, a new defense that targets intrinsic requirements of effective GNN backdoors rather than surface-level cues. Our key observation is that flipping a victim node's prediction requires substantial influence on the victim: attackers tend to either inject many trigger nodes or rely on a small set of highly influential ones. Building on this observation, PRAETORIAN (i) analyzes internal correlations within potential trigger subgraphs to detect abnormally large injected structures, and (ii) quantifies external node influence to identify triggers with disproportionate impact. Across our evaluations, PRAETORIAN reduces the average attack success rate (ASR) to 0.55% with only a 0.62% drop in clean accuracy (CA), whereas state-of-the-art defenses still yield an average ASR of >20% and a CA drop of >3% under the same conditions. Moreover, PRAETORIAN remains effective against a range of adaptive attacks, forcing adversaries to either inject many trigger nodes to achieve high ASR (>80%), which incurs a >10% CA drop, or preserve CA at the cost of limiting ASR to 18.1%. Overall, PRAETORIAN constrains attackers to an unfavorable trade-off between efficacy and detectability.

Momentum

Related topics

Latest papers 34

Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors

Activation Differences Reveal Backdoors: A Comparison of SAE Architectures

BehaviorGuard: Online Backdoor Defense for Deep Reinforcement Learning

Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning