Profiles2021-2025
Jie Shi
Huawei International
9Papers
3Last author
28Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers9
- Multi-Turn Jailbreaking Large Language Models via Attention ShiftingAuthor 7 of 7AAAI 2025 · 26 citations
- ACE: Concept Editing in Diffusion Models without Performance DegradationAuthor 5 of 7ACM MM 2025
- ADBM: Adversarial Diffusion Bridge Model for Reliable Adversarial PurificationAuthor 7 of 8ICLR 2025
- PBCAT: Patch-Based Composite Adversarial Training Against Physically Realizable Attacks on Object DetectionAuthor 6 of 7ICCV 2025
- Towards Neuron Attributions in Multi-Modal Large Language ModelsAuthor 8 of 10NeurIPS 2024 · 16 citations
- Differential Aggregation against General Colluding AttackersAuthor 7 of 7ICDE 2023 · 11 citations
- MExMI: Pool-based Active Model Extraction Crossover Membership InferenceAuthor 6 of 6NeurIPS 2022 · 17 citations
- Backdoor Pre-trained Models Can Transfer to AllAuthor 6 of 8CCS 2021 · 72 citations
- Cert-RNN: Towards Certifying the Robustness of Recurrent Neural NetworksAuthor 6 of 9CCS 2021 · 25 citations
