Profiles2018-2024
Guanhong Tao
Purdue University
21Papers
0Last author
44Unique co-authors
2First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers21
- Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object DetectionAuthor 5 of 8ICLR 2024 · 32 citations
- On Large Language Models' Resilience to Coercive InterrogationAuthor 3 of 5S&P 2024 · 24 citations
- Gradient Shaping: Enhancing Backdoor Attack Against Reverse EngineeringAuthor 5 of 8NDSS 2024
- ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLPAuthor 3 of 7NeurIPS 2023 · 37 citations
- Improving Binary Code Similarity Transformer Models by Semantics-Driven Instruction DeemphasisAuthor 7 of 10ISSTA 2023 · 25 citations
- Backdooring Neural Code SearchAuthor 3 of 7ACL 2023 · 18 citations
- Django: Detecting Trojans in Object Detection Models via Gaussian Focus CalibrationAuthor 3 of 9NeurIPS 2023 · 18 citations
- PEM: Representing Binary Program Semantics for Similarity Analysis via a Probabilistic Execution ModelAuthor 7 of 10FSE 2023 · 8 citations
- Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World AttacksAuthor 3 of 5ICLR 2023 · 6 citations
- MEDIC: Remove Model Backdoors via Importance Driven CloningAuthor 2 of 8CVPR 2023
- Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor DefenseAuthor 3 of 8ICML 2022 · 58 citations
- Complex Backdoor Detection by Symmetric Feature DifferencingAuthor 3 of 6CVPR 2022 · 35 citations
- RULER: discriminative and iterative adversarial training for deep neural network fairnessAuthor 1 of 4FSE 2022 · 29 citations
- Bounded Adversarial Attack on Deep Content FeaturesAuthor 2 of 3CVPR 2022 · 7 citations
- OSPREY: Recovery of Variable and Data Structure via Probabilistic Analysis for Stripped BinaryAuthor 4 of 8S&P 2021 · 78 citations
- StochFuzz: Sound and Cost-effective Fuzzing of Stripped Binaries by Incremental and Stochastic RewritingAuthor 3 of 6S&P 2021 · 53 citations
- Towards Feature Space Adversarial Attack by Style PerturbationAuthor 2 of 4AAAI 2021 · 33 citations
- Correlations between deep neural network model coverage criteria and model qualityAuthor 2 of 7FSE 2020 · 75 citations
- TRADER: trace divergence analysis and embedding regulation for debugging recurrent neural networksAuthor 1 of 5ICSE 2020 · 14 citations
- NIC: Detecting Adversarial Samples with Neural Network Invariant CheckingAuthor 3 of 5NDSS 2019 · 283 citations
- Precise Android API Protection Mapping Derivation and ReasoningAuthor 2 of 5CCS 2018 · 51 citations
