Benjamin Zi Hao Zhao

69 papers A* 5A 4B 3Misc 2Journal 45Unranked 9
YearRankTypeTitle / Venue / Authors
2026 A conf
Forget Me, Not My Friends! Object Unlearning Based on Scene Graphs.
WSDM
Chenhan Zhang, Benjamin Zi Hao Zhao, Hassan Asghar, Weiqi Wang, An Liu, Dali Kaafar
2026 J jnl
Protecting User Prompts Via Character-Level Differential Privacy.
CoRR
Shashie Dilhara Batan Arachchige, Hassan Jameel Asghar, Benjamin Zi Hao Zhao, Dinusha Vatsalan, Dali Kaafar
2026 J jnl
dX-Privacy for Text and the Curse of Dimensionality.
Proc. Priv. Enhancing Technol.
Hassan Asghar, Robin Carpentier, Benjamin Zi Hao Zhao, Dali Kaafar
2025 J jnl
A Large-Scale Empirical Analysis of Custom GPTs' Vulnerabilities in the OpenAI Ecosystem.
CoRR
Sunday Oyinlola Ogundoyin, Muhammad Ikram, Hassan Jameel Asghar, Benjamin Zi Hao Zhao, Dali Kaafar
2025 A conf
CARE: Enhancing LLM Instruction Following via Dual-Agent Prompt Refinement.
ECAI
Nardine Basta, Benjamin Zi Hao Zhao, Muhammad Ikram, Mohamed Ali Kâafar
2025 — conf
CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs.
ACSAC Workshops
Shashie Dilhara Batan Arachchige, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Dinusha Vatsalan, Dali Kaafar
2025 J jnl
CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs.
CoRR
Shashie Dilhara Batan Arachchige, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Dinusha Vatsalan, Dali Kaafar
2025 — conf
Facing the Challenge of Leveraging Untrained Humans in Malware Analysis.
SEC (1)
Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Muhammad Ikram, Mohamed Ali Kâafar, Sean Lamont, Daniel Coscia
2025 J jnl
Privacy-Preserving IoT in Connected Aircraft Cabin.
CoRR
Nilesh Vyas, Benjamin Zi Hao Zhao, Aygün Baltaci, Gustavo de Carvalho Bertoli, Hassan Asghar, Markus Klügel, Gerrit Schramm, Martin Kubisch, Dali Kaafar
2025 — conf
Unsafe by Design? A First Look at Security and Privacy Risks in OpenAI's Custom GPT Ecosystem.
WPES
Sunday Oyinlola Ogundoyin, Muhammad Ikram, Hassan Jameel Asghar, Benjamin Zi Hao Zhao, Dali Kaafar
2024 A* conf
DNN-GP: Diagnosing and Mitigating Model's Faults Using Latent Concepts.
USENIX Security Symposium
Shuo Wang, Hongsheng Hu, Jiamin Chang, Benjamin Zi Hao Zhao, Qi Alfred Chen, Minhui Xue
2024 J jnl
Exploring the Distinctive Tweeting Patterns of Toxic Twitter Users.
CoRR
Hina Qayyum, Muhammad Ikram, Benjamin Zi Hao Zhao, Ian D. Wood, Nicolas Kourtellis, Mohamed Ali Kâafar
2024 J jnl
GPTs Window Shopping: An analysis of the Landscape of Custom ChatGPT Models.
CoRR
Benjamin Zi Hao Zhao, Muhammad Ikram, Mohamed Ali Kâafar
2024 A* conf
LACMUS: Latent Concept Masking for General Robustness Enhancement of DNNs.
SP
Shuo Wang, Hongsheng Hu, Jiamin Chang, Benjamin Zi Hao Zhao, Minhui Xue
2024 — conf
On Adversarial Training with Incorrect Labels.
WISE (4)
Benjamin Zi Hao Zhao, Junda Lu, Xiaowei Zhou, Dinusha Vatsalan, Muhammad Ikram, Mohamed Ali Kâafar
2024 J jnl
On mission Twitter Profiles: A Study of Selective Toxic Behavior.
CoRR
Hina Qayyum, Muhammad Ikram, Benjamin Zi Hao Zhao, Ian D. Wood, Nicolas Kourtellis, Mohamed Ali Kâafar
2024 — conf
On the Robustness of Malware Detectors to Adversarial Samples.
ESORICS Workshops (2)
Muhammad Salman, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Muhammad Ikram, Sidharth Kaushik, Mohamed Ali Kâafar
2024 J jnl
On the Robustness of Malware Detectors to Adversarial Samples.
CoRR
Muhammad Salman, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Muhammad Ikram, Sidharth Kaushik, Mohamed Ali Kâafar
2024 B conf
PPDL: Efficient Dropout-Resilient Aggregation for Privacy-Preserving Decentralized Learning.
NSS
Ali Reza Ghavamipour, Benjamin Zi Hao Zhao, Fatih Turkmen
2024 J jnl
Preempting Text Sanitization Utility in Resource-Constrained Privacy-Preserving LLM Interactions.
CoRR
Robin Carpentier, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Dali Kaafar
2024 J jnl
Privacy-Preserving Aggregation for Decentralized Learning with Byzantine-Robustness.
CoRR
Ali Reza Ghavamipour, Benjamin Zi Hao Zhao, Oguzhan Ersoy, Fatih Turkmen
2024 J jnl
Privacy-Preserving, Dropout-Resilient Aggregation in Decentralized Learning.
CoRR
Ali Reza Ghavamipour, Benjamin Zi Hao Zhao, Fatih Turkmen
2024 J jnl
SenTopX: Benchmark for User Sentiment on Various Topics.
CoRR
Hina Qayyum, Muhammad Ikram, Benjamin Zi Hao Zhao, Ian D. Wood, Mohamad Ali Kâafar, Nicolas Kourtellis
2024 J jnl
Targeted Therapy in Data Removal: Object Unlearning Based on Scene Graphs.
CoRR
Chenhan Zhang, Benjamin Zi Hao Zhao, Hassan Asghar, Dali Kaafar
2024 J jnl
Use of cryptography in malware obfuscation.
J. Comput. Virol. Hacking Tech.
Hassan Jameel Asghar, Benjamin Zi Hao Zhao, Muhammad Ikram, Giang Linh Duc Nguyen, Dali Kaafar, Sean Lamont, Daniel Coscia
2024 J jnl
d
CoRR
Hassan Jameel Asghar, Robin Carpentier, Benjamin Zi Hao Zhao, Dali Kaafar
2023 — conf
A longitudinal study of the top 1% toxic Twitter profiles.
WebSci
Hina Qayyum, Benjamin Zi Hao Zhao, Ian D. Wood, Muhammad Ikram, Nicolas Kourtellis, Mohamed Ali Kâafar
2023 J jnl
A longitudinal study of the top 1% toxic Twitter profiles.
CoRR
Hina Qayyum, Benjamin Zi Hao Zhao, Ian D. Wood, Muhammad Ikram, Mohamed Ali Kâafar, Nicolas Kourtellis
2023 J jnl
DDoD: Dual Denial of Decision Attacks on Human-AI Teams.
IEEE Pervasive Comput.
Benjamin Tag, Niels van Berkel, Sunny Verma, Benjamin Zi Hao Zhao, Shlomo Berkovsky, Dali Kaafar, Vassilis Kostakos, Olga Ohrimenko
2023 B conf
Exploring the Distinctive Tweeting Patterns of Toxic Twitter Users.
IEEE Big Data
Hina Qayyum, Muhammad Ikram, Benjamin Zi Hao Zhao, Ian D. Wood, Nicolas Kourtellis, Mohamed Ali Kâafar
2023 B conf
On mission Twitter Profiles: A Study of Selective Toxic Behavior.
IEEE Big Data
Hina Qayyum, Muhammad Ikram, Benjamin Zi Hao Zhao, Ian D. Wood, Nicolas Kourtellis, Mohamed Ali Kâafar
2023 — conf
Those Aren't Your Memories, They're Somebody Else's: Seeding Misinformation in Chat Bot Memories.
ACNS (1)
Conor Atkins, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Ian D. Wood, Mohamed Ali Kâafar
2023 J jnl
Those Aren't Your Memories, They're Somebody Else's: Seeding Misinformation in Chat Bot Memories.
CoRR
Conor Atkins, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Ian D. Wood, Mohamed Ali Kâafar
2023 J jnl
Unintended Memorization and Timing Attacks in Named Entity Recognition Models.
Proc. Priv. Enhancing Technol.
Rana Salal Ali, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Tham Nguyen, Ian David Wood, Mohamed Ali Kâafar
2022 J jnl
A deep dive into the consistently toxic 1% of Twitter.
CoRR
Hina Qayyum, Benjamin Zi Hao Zhao, Ian D. Wood, Muhammad Ikram, Mohamed Ali Kâafar, Nicolas Kourtellis
2022 J jnl
Backdoors Against Natural Language Processing: A Review.
IEEE Secur. Priv.
Shaofeng Li, Tian Dong, Benjamin Zi Hao Zhao, Minhui Xue, Suguo Du, Haojin Zhu
2022 J jnl
DDoD: Dual Denial of Decision Attacks on Human-AI Teams.
CoRR
Benjamin Tag, Niels van Berkel, Sunny Verma, Benjamin Zi Hao Zhao, Shlomo Berkovsky, Dali Kaafar, Vassilis Kostakos, Olga Ohrimenko
2022 — ch.
Deep Learning Backdoors.
Security and Artificial Intelligence
Shaofeng Li, Shiqing Ma, Minhui Xue, Benjamin Zi Hao Zhao
2022 J jnl
SoK: Use of Cryptography in Malware Obfuscation.
CoRR
Hassan Jameel Asghar, Benjamin Zi Hao Zhao, Muhammad Ikram, Giang L. D. Nguyen, Dali Kaafar, Sean Lamont, Daniel Coscia
2022 J jnl
SoK: Use of Cryptography in Malware Obfuscation.
IACR Cryptol. ePrint Arch.
Hassan Jameel Asghar, Benjamin Zi Hao Zhao, Muhammad Ikram, Giang Linh Duc Nguyen, Dali Kaafar, Sean Lamont, Daniel Coscia
2022 J jnl
Unintended Memorization and Timing Attacks in Named Entity Recognition Models.
CoRR
Rana Salal Ali, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Tham Nguyen, Ian David Wood, Dali Kaafar
2021 A* conf
Hidden Backdoors in Human-Centric Language Models.
CCS
Shaofeng Li, Hui Liu, Tian Dong, Benjamin Zi Hao Zhao, Minhui Xue, Haojin Zhu, Jialiang Lu
2021 J jnl
Hidden Backdoors in Human-Centric Language Models.
CoRR
Shaofeng Li, Hui Liu, Tian Dong, Benjamin Zi Hao Zhao, Minhui Xue, Haojin Zhu, Jialiang Lu
2021 J jnl
Invisible Backdoor Attacks on Deep Neural Networks Via Steganography and Regularization.
IEEE Trans. Dependable Secur. Comput.
Shaofeng Li, Minhui Xue, Benjamin Zi Hao Zhao, Haojin Zhu, Xinpeng Zhang
2021 J jnl
MANDERA: Malicious Node Detection in Federated Learning via Ranking.
CoRR
Wanchuang Zhu, Benjamin Zi Hao Zhao, Simon Luo, Ke Deng
2021 A conf
On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Models.
EuroS&P
Benjamin Zi Hao Zhao, Aviral Agrawal, Catisha Coburn, Hassan Jameel Asghar, Raghav Bhaskar, Mohamed Ali Kâafar, Darren Webb, Peter Dickinson
2021 J jnl
On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Models.
CoRR
Benjamin Zi Hao Zhao, Aviral Agrawal, Catisha Coburn, Hassan Jameel Asghar, Raghav Bhaskar, Mohamed Ali Kâafar, Darren Webb, Peter Dickinson
2021 Misc conf
Oriole: Thwarting Privacy Against Trustworthy Deep Learning Models.
ACISP
Liuqiao Chen, Hu Wang, Benjamin Zi Hao Zhao, Minhui Xue, Haifeng Qian
2021 J jnl
Oriole: Thwarting Privacy against Trustworthy Deep Learning Models.
CoRR
Liuqiao Chen, Hu Wang, Benjamin Zi Hao Zhao, Minhui Xue, Haifeng Qian
2021 J jnl
The Audio Auditor: User-Level Membership Inference in Internet of Things Voice Services.
Proc. Priv. Enhancing Technol.
Yuantian Miao, Minhui Xue, Chao Chen, Lei Pan, Jun Zhang, Benjamin Zi Hao Zhao, Dali Kaafar, Yang Xiang
2021 J jnl
With Great Dispersion Comes Greater Resilience: Efficient Poisoning Attacks and Defenses for Linear Regression Models.
IEEE Trans. Inf. Forensics Secur.
Jialin Wen, Benjamin Zi Hao Zhao, Minhui Xue, Alina Oprea, Haifeng Qian
2020 J jnl
Deep Learning Backdoors.
CoRR
Shaofeng Li, Shiqing Ma, Minhui Xue, Benjamin Zi Hao Zhao
2020 J jnl
Exploiting Behavioral Side Channels in Observation Resilient Cognitive Authentication Schemes.
ACM Trans. Priv. Secur.
Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Mohamed Ali Kâafar, Francesca Trevisan, Haiyue Yuan
2020 J jnl
Exploiting Behavioral Side-Channels in Observation Resilient Cognitive Authentication Schemes.
CoRR
Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Mohamed Ali Kâafar, Francesca Trevisan, Haiyue Yuan
2020 — conf
Not one but many Tradeoffs: Privacy Vs. Utility in Differentially Private Machine Learning.
CCSW
Benjamin Zi Hao Zhao, Mohamed Ali Kâafar, Nicolas Kourtellis
2020 J jnl
Not one but many Tradeoffs: Privacy Vs. Utility in Differentially Private Machine Learning.
CoRR
Benjamin Zi Hao Zhao, Mohamed Ali Kâafar, Nicolas Kourtellis
2020 A* conf
On the Resilience of Biometric Authentication Systems against Random Inputs.
NDSS
Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Mohamed Ali Kâafar
2020 J jnl
On the Resilience of Biometric Authentication Systems against Random Inputs.
CoRR
Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Mohamed Ali Kâafar
2020 Misc conf
PALOR: Poisoning Attacks Against Logistic Regression.
ACISP
Jialin Wen, Benjamin Zi Hao Zhao, Minhui Xue, Haifeng Qian
2020 J jnl
With Great Dispersion Comes Greater Resilience: Efficient Poisoning Attacks and Defenses for Online Regression Models.
CoRR
Jialin Wen, Benjamin Zi Hao Zhao, Minhui Xue, Haifeng Qian
2019 A conf
A Decade of Mal-Activity Reporting: A Retrospective Analysis of Internet Malicious Activity Blacklists.
AsiaCCS
Benjamin Zi Hao Zhao, Muhammad Ikram, Hassan Jameel Asghar, Mohamed Ali Kâafar, Abdelberi Chaabane, Kanchana Thilakarathna
2019 J jnl
A Decade of Mal-Activity Reporting: A Retrospective Analysis of Internet Malicious Activity Blacklists.
CoRR
Benjamin Zi Hao Zhao, Muhammad Ikram, Hassan Jameel Asghar, Mohamed Ali Kâafar, Abdelberi Chaabane, Kanchana Thilakarathna
2019 J jnl
Invisible Backdoor Attacks Against Deep Neural Networks.
CoRR
Shaofeng Li, Benjamin Zi Hao Zhao, Jiahao Yu, Minhui Xue, Dali Kaafar, Haojin Zhu
2019 J jnl
On Inferring Training Data Attributes in Machine Learning Models.
CoRR
Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Raghav Bhaskar, Mohamed Ali Kâafar
2019 J jnl
The Audio Auditor: Participant-Level Membership Inference in Voice-Based IoT.
CoRR
Yuantian Miao, Benjamin Zi Hao Zhao, Minhui Xue, Chao Chen, Lei Pan, Jun Zhang, Dali Kaafar, Yang Xiang
2018 J jnl
Touch and You're Trapp(ck)ed: Quantifying the Uniqueness of Touch Gestures for Tracking.
Proc. Priv. Enhancing Technol.
Rahat Masood, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Mohamed Ali Kâafar
2017 — conf
BehavioCog: An Observation Resistant Authentication Scheme.
Financial Cryptography
Jagmohan Chauhan, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Jonathan Chan, Mohamed Ali Kâafar
2017 A* conf
POSTER: TouchTrack: How Unique are your Touch Gestures?
CCS
Rahat Masood, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Mohamed Ali Kâafar
2016 J jnl
BehavioCog: An Observation Resistant Authentication Scheme.
CoRR
Jagmohan Chauhan, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Jonathan Chan, Mohamed Ali Kâafar