2 citations · 4 across the 8 of their papers we have counts for
8 papers
Safety, Security, and Cognitive Risks in Neuro-Symbolic AI
Manoj Parmar
Neuro-symbolic AI (NeSy) pairs neural perception with symbolic reasoning, making it attractive for high-stakes domains where explainability and structured inference are required. H…
Safety, Security, and Cognitive Risks in World Models
Manoj Parmar
World models - learned internal simulators of environment dynamics - are rapidly becoming foundational to autonomous decision-making in robotics, autonomous vehicles, and agentic A…
Safety, Security, and Cognitive Risks in State-Space Models: A Systematic Threat Analysis with Spectral, Stateful, and Capacity Attacks
Manoj Parmar
State-Space Models (SSMs) -- structured SSMs (S4, S4D, DSS, S5), selective SSMs (Mamba, Mamba-2), and hybrid architectures (Jamba) -- are deployed in safety-critical long-context a…
Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies
Manojkumar Parmar, Yuvaraj Govindarajulu
Large Language Models (LLMs) have achieved remarkable progress in reasoning, alignment, and task-specific performance. However, ensuring harmlessness in these systems remains a cri…
VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces
Somnath Sendhil Kumar, Yuvaraj Govindarajulu, Pavan Kulkarni +1
In the domain of black-box model extraction, conventional methods reliant on soft labels or surrogate datasets struggle with scaling to high-dimensional input spaces and managing t…
Enhancing TinyML Security: Study of Adversarial Attack Transferability
Parin Shah, Yuvaraj Govindarajulu, Pavan Kulkarni +1
The recent strides in artificial intelligence (AI) and machine learning (ML) have propelled the rise of TinyML, a paradigm enabling AI computations at the edge without dependence o…
MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception
Vidit Khazanchi, Pavan Kulkarni, Yuvaraj Govindarajulu +1
Emerging vulnerabilities in machine learning (ML) models due to adversarial attacks raise concerns about their reliability. Specifically, evasion attacks manipulate models by intro…
On the notion of Hallucinations from the lens of Bias and Validity in Synthetic CXR Images
Gauri Bhardwaj, Yuvaraj Govindarajulu, Sundaraparipurnan Narayanan +2
Medical imaging has revolutionized disease diagnosis, yet the potential is hampered by limited access to diverse and privacy-conscious datasets. Open-source medical datasets, while…