Mahmood Sharif / Mahmood Sharif Source Themes Academic (https://sourcethemes.com/academic/)en-usSat, 01 Aug 2026 00:00:00 +0000 /images/icon_hu17ec3f4c5dad74ee902e9428b7d65766_36835_512x512_fill_lanczos_center_3.png Mahmood Sharif / Sy-FAR: Symmetry-based Fair Adversarial Robustness /publication/usenix26-sy-far/ Sat, 01 Aug 2026 00:00:00 +0000 /publication/usenix26-sy-far/ Backdooring Acoustic Foundation Models for Physically Realizable Triggers /publication/raid26-fab/ Wed, 01 Jul 2026 00:00:00 +0000 /publication/raid26-fab/ Reconstructing Template-Memorized Images from Natural Prompts /publication/icml26-tmi/ Mon, 02 Mar 2026 00:00:00 +0000 /publication/icml26-tmi/ How Probing for Problems and Bias Affects Perceptions of AI Chatbot Trustworthiness /publication/facct26-ai-trust-preceptions/ Sun, 01 Mar 2026 00:00:00 +0000 /publication/facct26-ai-trust-preceptions/ Universal Jailbreak Suffixes Are Strong Attention Hijackers /publication/tacl26-hijacking/ Sun, 01 Mar 2026 00:00:00 +0000 /publication/tacl26-hijacking/ NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models /publication/iclr26-noiseprints/ Fri, 27 Feb 2026 00:00:00 +0000 /publication/iclr26-noiseprints/ Safeguarding Language Models via Self-Destruct Trapdoor /publication/eacl26-self-destruct/ Fri, 20 Feb 2026 00:00:00 +0000 /publication/eacl26-self-destruct/ Bot Among Us: Exploring User Awareness and Privacy Concerns About Chatbots in Group Chats /publication/pets26-chatbots/ Sun, 01 Feb 2026 00:00:00 +0000 /publication/pets26-chatbots/ GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search /publication/ccs25-gaselite/ Wed, 01 Oct 2025 00:00:00 +0000 /publication/ccs25-gaselite/ Safety Perceptions of Generative AI Conversational Agents: Uncovering Perceptual Differences in Trust, Risk, and Fairness /publication/soups25-chatbot-safety-perceptions/ Tue, 01 Jul 2025 00:00:00 +0000 /publication/soups25-chatbot-safety-perceptions/ On a Scale of 1 to 5, How Reliable Are AI User Studies? A Call for Developing Validated, Meaningful Scales and Metrics about User Perceptions of AI Systems /publication/conpro25-ai-trust-scales/ Tue, 01 Apr 2025 00:00:00 +0000 /publication/conpro25-ai-trust-scales/ Training Robust ML-based Raw-Binary Malware Detectors in Hours, not Months /publication/ccs24-malware-robustness/ Sun, 20 Oct 2024 00:00:00 +0000 /publication/ccs24-malware-robustness/ Harmful Bias: A General Label-Leakage Attack on Federated Learning from Bias Gradients /publication/aisec24-label-leakage/ Sat, 19 Oct 2024 00:00:00 +0000 /publication/aisec24-label-leakage/ The Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data Augmentations /publication/aisec24-ultimate-combo/ Sat, 19 Oct 2024 00:00:00 +0000 /publication/aisec24-ultimate-combo/ Privacy-Preserving Collaborative Genomic Research: A Real-Life Deployment and Vision /publication/healthsec24-vision/ Fri, 18 Oct 2024 00:00:00 +0000 /publication/healthsec24-vision/ A High Coverage Cybersecurity Scale Predictive of User Behavior /publication/usenix24-esbs/ Sun, 01 Sep 2024 00:00:00 +0000 /publication/usenix24-esbs/ CaFA: Cost-aware, Feasible Attacks With Database Constraints Against Neural Tabular Classifiers /publication/oakland24-cafa/ Mon, 20 May 2024 00:00:00 +0000 /publication/oakland24-cafa/ DrSec: Flexible Distributed Representations for Efficient Endpoint Security /publication/oakland24-drsec/ Mon, 20 May 2024 00:00:00 +0000 /publication/oakland24-drsec/ Group-based Robustness: A General Framework for Customized Robustness in the Real World /publication/ndss24-gbr/ Mon, 26 Feb 2024 00:00:00 +0000 /publication/ndss24-gbr/ Accessorize in the Dark: A Security Analysis of Near-Infrared Face Recognition /publication/esorics23-nir-attacks/ Tue, 01 Aug 2023 00:00:00 +0000 /publication/esorics23-nir-attacks/ Adversarial Training for Raw-Binary Malware Classifiers /publication/usenix23-malware-advtrain/ Tue, 01 Aug 2023 00:00:00 +0000 /publication/usenix23-malware-advtrain/ Property-Driven Evaluation of RL-Controllers in Self-Driving Datacenters /publication/dmml22-rl-controllers/ Tue, 25 Oct 2022 00:00:00 +0000 /publication/dmml22-rl-controllers/ Scalable Verification of GNN-based Job Schedulers /publication/oopsla22-gnn-verify/ Thu, 01 Sep 2022 00:00:00 +0000 /publication/oopsla22-gnn-verify/ "I Have No Idea What a Social Bot Is": On Users' Perceptions of Social Bots and Ability to Detect Them /publication/hai22-bots/ Wed, 31 Aug 2022 00:00:00 +0000 /publication/hai22-bots/ Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks /publication/icml22-cgd/ Sun, 15 May 2022 00:00:00 +0000 /publication/icml22-cgd/ Malware Makeover: Breaking ML-based Static Analysis by Modifying Executable Bytes /publication/asiaccs21-malware/ Mon, 15 Feb 2021 00:00:00 +0000 /publication/asiaccs21-malware/ How Risky Are Real Users' IFTTT Applets? /publication/soups20-ifttt/ Fri, 01 May 2020 00:00:00 +0000 /publication/soups20-ifttt/ Training Older Adults to Resist Scams with Fraud Bingo and Scam-Detection Challenges /publication/chiw20-older-adults/ Wed, 01 Apr 2020 00:00:00 +0000 /publication/chiw20-older-adults/ $n$-ML: Mitigating Adversarial Examples via Ensembles of Topologically Manipulated Classifiers /publication/arxiv19-nml/ Sun, 01 Dec 2019 00:00:00 +0000 /publication/arxiv19-nml/ Practical Inference-Time Attacks Against Machine-Learning Systems and a Defense Against Them /publication/thesis19-phd-cmu-ece/ Mon, 11 Nov 2019 00:00:00 +0000 /publication/thesis19-phd-cmu-ece/ A General Framework for Adversarial Examples with Objectives /publication/tops19-adv-ml/ Sat, 01 Jun 2019 00:00:00 +0000 /publication/tops19-adv-ml/ A Field Study of Computer-Security Perceptions Using Anti-Virus Customer-Support Chats /publication/chi19-customer-support/ Wed, 01 May 2019 00:00:00 +0000 /publication/chi19-customer-support/ Comparing Hypothetical and Realistic Privacy Valuations /publication/wpes18-privacy-valuations/ Mon, 01 Oct 2018 00:00:00 +0000 /publication/wpes18-privacy-valuations/ Predicting Impending Exposure to Malicious Content from User Behavior /publication/ccs18-exposure-prediction/ Mon, 01 Oct 2018 00:00:00 +0000 /publication/ccs18-exposure-prediction/ On the Suitability of $L_p$-norms for Creating and Preventing Adversarial Examples /publication/cvprw18-lpnorm/ Fri, 01 Jun 2018 00:00:00 +0000 /publication/cvprw18-lpnorm/ Riding Out DOMsday: Toward Detecting and Preventing DOM Cross-Site Scripting /publication/ndss18-dom-xss/ Thu, 01 Feb 2018 00:00:00 +0000 /publication/ndss18-dom-xss/ Topics of Controversy: An Empirical Analysis of Web Censorship Lists /publication/pets17-censorship/ Sat, 01 Jul 2017 00:00:00 +0000 /publication/pets17-censorship/ Self-Confidence Trumps Knowledge: A Cross-Cultural Study of Security Behavior /publication/chi17-cross-cultural-study/ Mon, 01 May 2017 00:00:00 +0000 /publication/chi17-cross-cultural-study/ Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition /publication/ccs16-adv-ml/ Sat, 01 Oct 2016 00:00:00 +0000 /publication/ccs16-adv-ml/ (Do Not) Track Me Sometimes: Users' Contextual Preferences for Web Tracking /publication/pets16-online-tracking/ Fri, 01 Jul 2016 00:00:00 +0000 /publication/pets16-online-tracking/