401 citations · 529 across the 35 of their papers we have counts for
37 papers
Attention Without Grounding: Causal Evaluation of Visual Explanations in Medical VLMs
Binesh Sadanandan, Vahid Behzadan
Attention and saliency heatmaps are widely used to explain medical Vision-Language Model (VLM) outputs on chest X-rays, yet whether they truly highlight the image evidence driving…
Predictive Entropy as a Joint Screen for Error and Paraphrase Instability in Medical Vision-Language Models
Binesh Sadanandan, Vahid Behzadan
Medical Vision-Language Models (VLMs) answering binary presence questions on chest radiographs can fail in two linked ways: they are confidently wrong, and they change answers when…
When Chain-of-Thought Backfires: Evaluating Prompt Sensitivity in Medical Language Models
Binesh Sadanandan, Vahid Behzadan
Large Language Models (LLMs) are increasingly deployed in medical settings, yet their sensitivity to prompt formatting remains poorly characterized. We evaluate MedGemma (4B and 27…
Consistent but Dangerous: Per-Sample Safety Classification Reveals False Reliability in Medical Vision-Language Models
Binesh Sadanandan, Vahid Behzadan
Consistency under paraphrase, the property that semantically equivalent prompts yield identical predictions, is increasingly used as a proxy for reliability when deploying medical…
Mechanistically Guided LoRA Improves Paraphrase Consistency in Medical Vision-Language Models
Binesh Sadanandan, Vahid Behzadan
Medical Vision-Language Models can give different yes or no answers to rephrasings of the same clinical question. We study this in MedGemma-4B using PSF-Med Sadanandan and Behzadan…
PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models
Binesh Sadanandan, Vahid Behzadan
Medical Vision Language Models (VLMs) can change their answers when clinicians rephrase the same question, a failure mode that threatens deployment safety. We introduce PSF-Med, a…
VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Models
Binesh Sadanandan, Vahid Behzadan
Vision Language Models (VLMs) hold great promise for streamlining labour-intensive medical imaging workflows, yet systematic security evaluations in clinical settings remain scarce…
Promise of Data-Driven Modeling and Decision Support for Precision Oncology and Theranostics
Binesh Sadanandan, Vahid Behzadan
Cancer remains a leading cause of death worldwide, necessitating personalized treatment approaches to improve outcomes. Theranostics, combining molecular-level imaging with targete…
Comparative Study of Generative Models for Early Detection of Failures in Medical Devices
Binesh Sadanandan, Bahareh Arghavani Nobar, Vahid Behzadan
The medical device industry has significantly advanced by integrating sophisticated electronics like microchips and field-programmable gate arrays (FPGAs) to enhance the safety and…
Cognitive Overload Attack:Prompt Injection for Long Context
Bibek Upadhayay, Vahid Behzadan, Amin Karbasi
Large Language Models (LLMs) have demonstrated remarkable capabilities in performing tasks across various domains without needing explicit retraining. This capability, known as In-…
Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs
Bibek Upadhayay, Vahid Behzadan
Large Language Models (LLMs) are increasingly being developed and applied, but their widespread use faces challenges. These include aligning LLMs' responses with human values to pr…
Robust Coordination under Misaligned Communication via Power Regularization
Nancirose Piazza, Amirhossein Karimia, Behnia Soleymanib +2
Effective communication in Multi-Agent Reinforcement Learning (MARL) can significantly enhance coordination and collaborative performance in complex and partially observable enviro…
TaCo: Enhancing Cross-Lingual Transfer for Low-Resource Languages in LLMs through Translation-Assisted Chain-of-Thought Processes
Bibek Upadhayay, Vahid Behzadan
Creating multilingual LLMs poses a significant challenge. Pretraining or fine-tuning LLMs to adopt new languages is evidently very costly. Furthermore, there exist limitations conc…
A Theory of Mind Approach as Test-Time Mitigation Against Emergent Adversarial Communication
Nancirose Piazza, Vahid Behzadan
Multi-Agent Systems (MAS) is the study of multi-agent interactions in a shared environment. Communication for cooperation is a fundamental construct for sharing information in part…
Adversarial Stimuli: Attacking Brain-Computer Interfaces via Perturbed Sensory Events
Bibek Upadhayay, Vahid Behzadan
Machine learning models are known to be vulnerable to adversarial perturbations in the input domain, causing incorrect predictions. Inspired by this phenomenon, we explore the feas…
Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)
Nancirose Piazza, Vahid Behzadan
Deep reinforcement learning (DRL) policies are vulnerable to unauthorized replication attacks, where an adversary exploits imitation learning to reproduce target policies from obse…
Adversarial Poisoning Attacks and Defense for General Multi-Class Models Based On Synthetic Reduced Nearest Neighbors
Pooya Tavallali, Vahid Behzadan, Peyman Tavallali +1
State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data…
Adversarial Attacks on Deep Algorithmic Trading Policies
Yaser Faghan, Nancirose Piazza, Vahid Behzadan +1
Deep Reinforcement Learning (DRL) has become an appealing solution to algorithmic trading such as high frequency trading of stocks and cyptocurrencies. However, DRL have been shown…
Sentimental LIAR: Extended Corpus and Deep Learning Models for Fake Claim Classification
Bibek Upadhayay, Vahid Behzadan
The rampant integration of social media in our every day lives and culture has given rise to fast and easier access to the flow of information than ever in human history. However,…
Founding The Domain of AI Forensics
Ibrahim Baggili, Vahid Behzadan
With the widespread integration of AI in everyday and critical technologies, it seems inevitable to witness increasing instances of failure in AI systems. In such cases, there aris…
A Novel Approach for Detection and Ranking of Trendy and Emerging Cyber Threat Events in Twitter Streams
Avishek Bose, Vahid Behzadan, Carlos Aguirre +1
We present a new machine learning and text information extraction approach to detection of cyber threat events in Twitter that are novel (previously non-extant) and developing (mar…
Sequential Triggers for Watermarking of Deep Reinforcement Learning Policies
Vahid Behzadan, William Hsu
This paper proposes a novel scheme for the watermarking of Deep Reinforcement Learning (DRL) policies. This scheme provides a mechanism for the integration of a unique identifier w…
Adversarial Exploitation of Policy Imitation
Vahid Behzadan, William Hsu
This paper investigates a class of attacks targeting the confidentiality aspect of security in Deep Reinforcement Learning (DRL) policies. Recent research have established the vuln…
Analysis and Improvement of Adversarial Training in DQN Agents With Adversarially-Guided Exploration (AGE)
Vahid Behzadan, William Hsu
This paper investigates the effectiveness of adversarial training in enhancing the robustness of Deep Q-Network (DQN) policies to state-space perturbations. We first present a form…