20 citations · 50 across the 14 of their papers we have counts for
16 papers
COPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol (MCP) Layers
Nahom Birhan, Mehrdad Rostamzadeh, Sidhant Narula +3
Large language models increasingly mediate tool use in Model Context Protocol (MCP) systems, where adversarial influence may enter through user instructions, tool schemas, tool out…
TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers
Mehrdad Rostamzadeh, Sidhant Narula, Mohammad Ghasemigol +1
The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model agents to external tool backends. This openness introduces a severe server-side t…
MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security
Mehrdad Rostamzadeh, Sidhant Narula, Nahom Birhan +2
The Model Context Protocol (MCP) enables large language models (LLMs) to dynamically discover and invoke third-party tools, significantly expanding agent capabilities while introdu…
BioShield: A Context-Aware Firewall for Securing Bio-LLMs
Protiva Das, Sovon Chakraborty, Sidhant Narula +5
The rapid advancement of Large Language Models (LLMs) in biological research has significantly lowered the barrier to accessing complex bioinformatics knowledge, ex perimental desi…
DCInject: Persistent Backdoor Attacks via Frequency Manipulation in Personal Federated Learning
Nahom Birhan, Daniel Wesego, Dereje Shenkut +2
Personalized federated learning (PFL) creates client-specific models to handle data heterogeneity. Previously, PFL has been shown to be naturally resistant to backdoor attack propa…
HarmNet: A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models
Sidhant Narula, Javad Rafiei Asl, Mohammad Ghasemigol +2
Large Language Models (LLMs) remain vulnerable to multi-turn jailbreak attacks. We introduce HarmNet, a modular framework comprising ThoughtNet, a hierarchical semantic network; a…
NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks
Javad Rafiei Asl, Sidhant Narula, Mohammad Ghasemigol +2
Large Language Models (LLMs) have revolutionized natural language processing but remain vulnerable to jailbreak attacks, especially multi-turn jailbreaks that distribute malicious…
MOFHEI: Model Optimizing Framework for Fast and Efficient Homomorphically Encrypted Neural Network Inference
Parsa Ghazvinian, Robert Podschwadt, Prajwal Panzade +2
Due to the extensive application of machine learning (ML) in a wide range of fields and the necessity of data privacy, privacy-preserving machine learning (PPML) solutions have rec…
SSCAE -- Semantic, Syntactic, and Context-aware natural language Adversarial Examples generator
Javad Rafiei Asl, Mohammad H. Rafiei, Manar Alohaly +1
Machine learning models are vulnerable to maliciously crafted Adversarial Examples (AEs). Training a machine learning model with AEs improves its robustness and stability against a…
RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning
Javad Rafiei Asl, Prajwal Panzade, Eduardo Blanco +2
Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite thei…
I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption
Prajwal Panzade, Daniel Takabi, Zhipeng Cai
In today's machine learning landscape, fine-tuning pretrained transformer models has emerged as an essential technique, particularly in scenarios where access to task-aligned train…
MedBlindTuner: Towards Privacy-preserving Fine-tuning on Biomedical Images with Transformers and Fully Homomorphic Encryption
Prajwal Panzade, Daniel Takabi, Zhipeng Cai
Advancements in machine learning (ML) have significantly revolutionized medical image analysis, prompting hospitals to rely on external ML services. However, the exchange of sensit…
An Insider Threat Mitigation Framework Using Attribute Based Access Control
Olusesi Balogun, Daniel Takabi
Insider Threat is a significant and potentially dangerous security issue in corporate settings. It is difficult to mitigate because, unlike external threats, insiders have knowledg…
SoK: Privacy Preserving Machine Learning using Functional Encryption: Opportunities and Challenges
Prajwal Panzade, Daniel Takabi
With the advent of functional encryption, new possibilities for computation on encrypted data have arisen. Functional Encryption enables data owners to grant third-party access to…
SoK: Privacy-preserving Deep Learning with Homomorphic Encryption
Robert Podschwadt, Daniel Takabi, Peizhao Hu
Outsourced computation for neural networks allows users access to state of the art models without needing to invest in specialized hardware and know-how. The problem is that the us…
Privacy preserving Neural Network Inference on Encrypted Data with GPUs
Daniel Takabi, Robert Podschwadt, Jeff Druce +2
Machine Learning as a Service (MLaaS) has become a growing trend in recent years and several such services are currently offered. MLaaS is essentially a set of services that provid…