Vahid Behzadan

66 papers A* 2A 2B 4C 5Journal 38Unranked 15

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Consistent but Dangerous: Per-Sample Safety Classification Reveals False Reliability in Medical Vision-Language Models. CoRR Binesh Sadanandan, Vahid Behzadan
2026	J	`jnl`	Mechanistically Guided LoRA Improves Paraphrase Consistency in Medical Vision-Language Models. CoRR Binesh Sadanandan, Vahid Behzadan
2026	J	`jnl`	PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models. CoRR Binesh Sadanandan, Vahid Behzadan
2026	J	`jnl`	When Chain-of-Thought Backfires: Evaluating Prompt Sensitivity in Medical Language Models. CoRR Binesh Sadanandan, Vahid Behzadan
2025	J	`jnl`	Comparative Study of Generative Models for Early Detection of Failures in Medical Devices. CoRR Binesh Sadanandan, Bahareh Arghavani Nobar, Vahid Behzadan
2025	J	`jnl`	Promise of Data-Driven Modeling and Decision Support for Precision Oncology and Theranostics. CoRR Binesh Sadanandan, Vahid Behzadan
2025	A	`conf`	Robust Coordination Under Misaligned Communication via Power Regularization. ECAI Nancirose Piazza, Amirhossein Karimi, Behnia Soleymani, Vahid Behzadan, Stefan Sarkadi
2025	J	`jnl`	VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Models. CoRR Binesh Sadanandan, Vahid Behzadan
2025	J	`jnl`	X-Guard: Multilingual Guard Agent for Content Moderation. CoRR Bibek Upadhayay, Vahid Behzadan
2024	J	`jnl`	Cognitive Overload Attack:Prompt Injection for Long Context. CoRR Bibek Upadhayay, Vahid Behzadan, Amin Karbasi
2024	—	`conf`	Large Language Models for Automatic Standardization of Cyber Deception Plans based on the Adversary Engagement Ontology. MILCOM Nancirose Piazza, Bibek Upadhayay, Ronald Scarpa, Vahid Behzadan
2024	J	`jnl`	Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs. CoRR Bibek Upadhayay, Vahid Behzadan
2024	J	`jnl`	The Power in Communication: Power Regularization of Communication for Autonomy in Cooperative Multi-Agent Reinforcement Learning. CoRR Nancirose Piazza, Vahid Behzadan, Stefan Sarkadi
2023	A	`conf`	A Theory of Mind Approach as Test-Time Mitigation Against Emergent Adversarial Communication. AAMAS Nancirose Piazza, Vahid Behzadan
2023	J	`jnl`	A Theory of Mind Approach as Test-Time Mitigation Against Emergent Adversarial Communication. CoRR Nancirose Piazza, Vahid Behzadan
2023	B	`conf`	Adversarial Stimuli: Attacking Brain-Computer Interfaces via Perturbed Sensory Events. SMC Bibek Upadhayay, Vahid Behzadan
2023	J	`jnl`	TaCo: Enhancing Cross-Lingual Transfer for Low-Resource Languages in LLMs through Translation-Assisted Chain-of-Thought Processes. CoRR Bibek Upadhayay, Vahid Behzadan
2022	C	`conf`	A Novel Approach for Synthetic Reduced Nearest-Neighbor Leveraging Neural Networks. ICMLA Azar Alizadeh, Pooya Tavallali, Vahid Behzadan, Aditya Ranganath, Mukesh Singhal
2022	B	`conf`	Adversarial Label-Poisoning Attacks and Defense for General Multi-Class Models Based on Synthetic Reduced Nearest Neighbor. ICIP Pooya Tavallali, Vahid Behzadan, Azar Alizadeh, Aditya Ranganath, Mukesh Singhal
2022	J	`jnl`	Adversarial Stimuli: Attacking Brain-Computer Interfaces via Perturbed Sensory Events. CoRR Bibek Upadhayay, Vahid Behzadan
2022	A*	`conf`	Hybrid Deep Learning Model for Fake News Detection in Social Networks (Student Abstract). AAAI Bibek Upadhayay, Vahid Behzadan
2022	C	`conf`	Stochastic Induction of Decision Trees with Application to Learning Haar Trees. ICMLA Azar Alizadeh, Mukesh Singhal, Vahid Behzadan, Pooya Tavallali, Aditya Ranganath
2021	J	`jnl`	Adversarial Poisoning Attacks and Defense for General Multi-Class Models Based On Synthetic Reduced Nearest Neighbors. CoRR Pooya Tavallali, Vahid Behzadan, Peyman Tavallali, Mukesh Singhal
2021	J	`jnl`	Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles. IEEE Intell. Transp. Syst. Mag. Vahid Behzadan, Arslan Munir
2021	—	`conf`	Combating Human Trafficking via Automatic OSINT Collection, Validation and Fusion. ICWSM Workshops Bibek Upadhayay, Zeeshan Ahmed M. Lodhia, Vahid Behzadan
2021	J	`jnl`	Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP). CoRR Nancirose Piazza, Vahid Behzadan
2021	J	`jnl`	Security and Privacy Issues in Intelligent Transportation Systems: Classification and Challenges. IEEE Intell. Transp. Syst. Mag. Dalton A. Hahn, Arslan Munir, Vahid Behzadan
2021	A*	`conf`	State-Wise Adaptive Discounting from Experience (SADE): A Novel Discounting Scheme for Reinforcement Learning (Student Abstract). AAAI Milan Zinzuvadiya, Vahid Behzadan
2021	C	`conf`	Tracing Relevant Twitter Accounts Active in Cyber Threat Intelligence Domain by Exploiting Content and Structure of Twitter Network. ISI Avishek Bose, Shreya Gopal Sundari, Vahid Behzadan, William H. Hsu
2020	J	`jnl`	Adversarial Attacks on Deep Algorithmic Trading Policies. CoRR Yaser Faghan, Nancirose Piazza, Vahid Behzadan, Ali Fathi
2020	—	`conf`	Founding The Domain of AI Forensics. SafeAI@AAAI Vahid Behzadan, Ibrahim M. Baggili
2020	C	`conf`	Sentimental LIAR: Extended Corpus and Deep Learning Models for Fake Claim Classification. ISI Bibek Upadhayay, Vahid Behzadan
2020	J	`jnl`	Sentimental LIAR: Extended Corpus and Deep Learning Models for Fake Claim Classification. CoRR Bibek Upadhayay, Vahid Behzadan
2019	J	`jnl`	A Novel Approach for Detection and Ranking of Trendy and Emerging Cyber Threat Events in Twitter Streams. CoRR Avishek Bose, Vahid Behzadan, Carlos A. Aguirre, William H. Hsu
2019	B	`conf`	A novel approach for detection and ranking of trendy and emerging cyber threat events in Twitter streams. ASONAM Avishek Bose, Vahid Behzadan, Carlos A. Aguirre, William H. Hsu
2019	—	`conf`	Adversarial Exploitation of Policy Imitation. AISafety@IJCAI Vahid Behzadan, William H. Hsu
2019	J	`jnl`	Adversarial Exploitation of Policy Imitation. CoRR Vahid Behzadan, William H. Hsu
2019	J	`jnl`	Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE). CoRR Vahid Behzadan, William H. Hsu
2019	—	`conf`	Emergence of Addictive Behaviors in Reinforcement Learning Agents. SafeAI@AAAI Vahid Behzadan, Roman V. Yampolskiy, Arslan Munir
2019	J	`jnl`	Founding The Domain of AI Forensics. CoRR Ibrahim M. Baggili, Vahid Behzadan
2019	—	`conf`	RL-Based Method for Benchmarking the Adversarial Resilience and Robustness of Deep Reinforcement Learning Policies. SAFECOMP Workshops Vahid Behzadan, William H. Hsu
2019	J	`jnl`	RL-Based Method for Benchmarking the Adversarial Resilience and Robustness of Deep Reinforcement Learning Policies. CoRR Vahid Behzadan, William H. Hsu
2019	J	`jnl`	Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies. CoRR Vahid Behzadan, William H. Hsu
2019	C	`conf`	TrolleyMod v1.0: An Open-Source Simulation and Data-Collection Platform for Ethical Decision Making in Autonomous Vehicles. AIES Vahid Behzadan, James Minton, Arslan Munir
2019	—	`conf`	Watermarking of DRL Policies with Sequential Triggers. AISafety@IJCAI Vahid Behzadan, William H. Hsu
2018	—	`conf`	A Psychopathological Approach to Safety Engineering in AI and AGI. SAFECOMP Workshops Vahid Behzadan, Arslan Munir, Roman V. Yampolskiy
2018	J	`jnl`	A Psychopathological Approach to Safety Engineering in AI and AGI. CoRR Vahid Behzadan, Arslan Munir, Roman V. Yampolskiy
2018	—	`conf`	Adversarial Exploitation of Emergent Dynamics in Smart Cities. ISC2 Vahid Behzadan, Arslan Munir
2018	J	`jnl`	Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles. CoRR Vahid Behzadan, Arslan Munir
2018	—	`conf`	Corpus and Deep Learning Classifier for Collection of Cyber Threat Indicators in Twitter Stream. IEEE BigData Vahid Behzadan, Carlos A. Aguirre, Avishek Bose, William H. Hsu
2018	J	`jnl`	Emergence of Addictive Behaviors in Reinforcement Learning Agents. CoRR Vahid Behzadan, Roman V. Yampolskiy, Arslan Munir
2018	—	`conf`	Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise. SAFECOMP Workshops Vahid Behzadan, Arslan Munir
2018	J	`jnl`	Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise. CoRR Vahid Behzadan, Arslan Munir
2018	J	`jnl`	The Faults in Our Pi Stars: Security Issues and Open Challenges in Deep Reinforcement Learning. CoRR Vahid Behzadan, Arslan Munir
2018	J	`jnl`	TrolleyMod v1.0: An Open-Source Simulation and Data-Collection Platform for Ethical Decision Making in Autonomous Vehicles. CoRR Vahid Behzadan, James Minton, Arslan Munir
2017	J	`jnl`	A Game-Theoretic Model for Analysis and Design of Self-Organization Mechanisms in IoT. CoRR Vahid Behzadan, Banafsheh Rekabdar
2017	—	`conf`	A Game-Theoretic Model for Analysis and Design of Self-organization Mechanisms in IoT. GAMENETS Vahid Behzadan, Banafsheh Rekabdar
2017	J	`jnl`	Cyber-Physical Attacks on UAS Networks- Challenges and Open Research Problems. CoRR Vahid Behzadan
2017	J	`jnl`	Models and Framework for Adversarial Attacks on Complex Adaptive Systems. CoRR Vahid Behzadan, Arslan Munir
2017	B	`conf`	On Fighting Fire with Fire: Strategic Destabilization of Terrorist Networks. ASONAM Vahid Behzadan, Amin Nourmohammadi, Mehmet Hadi Gunes, Murat Yuksel
2017	—	`conf`	Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks. MLDM Vahid Behzadan, Arslan Munir
2017	J	`jnl`	Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks. CoRR Vahid Behzadan, Arslan Munir
2017	J	`jnl`	Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger. CoRR Vahid Behzadan, Arslan Munir
2016	J	`jnl`	Adaptive beam nulling in multihop ad hoc networks against a jammer in motion. Comput. Networks Suman Bhunia, Vahid Behzadan, Paulo Alexandre Regis, Shamik Sengupta
2015	—	`conf`	Enhancement of spectrum utilization in non-contiguous DSA with online defragmentation. MILCOM Suman Bhunia, Vahid Behzadan, Shamik Sengupta
2015	—	`conf`	Performance of Adaptive Beam Nulling in Multihop Ad-Hoc Networks under Jamming. HPCC/CSS/ICESS Suman Bhunia, Vahid Behzadan, Paulo Alexandre Regis, Shamik Sengupta