157 citations · 929 across the 89 of their papers we have counts for
99 papers
Creds: Privately Inferred Credentials
Samuel Breckenridge, Dani Vilardell, Derek Leung +4
Decentralized verifiable credential systems have seen limited deployment in practice. Existing constructions, built on zero-knowledge proofs, are complex, application-specific, and…
Estimating Mixture Distributions via Stochastic Mirror Descent
Mohammadreza Ahmadypour, Tara Javidi, Farinaz Koushanfar
We revisit the classical problem of estimating an unknown distribution from its samples by fitting a mixture model that minimizes cross-entropy loss. Framing the task as a stochast…
LLM Ghostbusters: Surgical Package Hallucination Suppression via Adaptive Unlearning
Joseph Spracklen, Pedram Aghazadeh, Farinaz Koushanfar +1
Hallucinations remain an unsolved problem for LLMs, and package hallucinations are a particularly dangerous instance of this phenomenon. Package hallucinations occur during code ge…
Trojans in Artificial Intelligence (TrojAI) Final Report
Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski +68
The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI T…
PAC to the Future: Zero-Knowledge Proofs of PAC Private Systems
Guilhem Repetto, Nojan Sheybani, Gabrielle De Micheli +1
Privacy concerns in machine learning systems have grown significantly with the increasing reliance on sensitive user data for training large-scale models. This paper introduces a n…
CryptoGen: Secure Transformer Generation with Encrypted KV-Cache Reuse
Hedong Zhang, Neusha Javidnia, Shweta Pardeshi +2
The widespread deployment of cloud-hosted generative models raises a fundamental challenge: enabling efficient autoregressive generation while preserving the privacy of both user p…
Beyond Perplexity: A Lightweight Benchmark for Knowledge Retention in Supervised Fine-Tuning
Soheil Zibakhsh Shabgahi, Pedram Aghazadeh, Farinaz Koushanfar
Supervised Fine-Tuning (SFT) is a standard approach for injecting domain knowledge into Large Language Models (LLMs). However, relying on validation perplexity to monitor training…
Test-Time Adaptation for Unsupervised Combinatorial Optimization
Yiqiao Liao, Farinaz Koushanfar, Parinaz Naghizadeh
Unsupervised neural combinatorial optimization (NCO) enables learning powerful solvers without access to ground-truth solutions. Existing approaches fall into two disjoint paradigm…
SWaRL: Safeguard Code Watermarking via Reinforcement Learning
Neusha Javidnia, Ruisi Zhang, Ashish Kundu +1
We present SWaRL, a robust and fidelity-preserving watermarking framework designed to protect the intellectual property of code LLMs by embedding unique and verifiable signatures i…
Optimizing Privacy-Preserving Primitives to Support LLM-Scale Applications
Yaman Jandali, Ruisi Zhang, Nojan Sheybani +1
Privacy-preserving technologies have introduced a paradigm shift that allows for realizable secure computing in real-world systems. The significant barrier to the practical adoptio…
ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version)
Nojan Sheybani, Alessandro Pegoraro, Jonathan Knauer +4
Split Learning (SL) is a distributed learning approach that enables resource-constrained clients to collaboratively train deep neural networks (DNNs) by offloading most layers to a…
ForTIFAI: Fending Off Recursive Training Induced Failure for AI Model Collapse
Soheil Zibakhsh Shabgahi, Pedram Aghazadeh, Azalia Mirhoseini +1
The increasing reliance on generative AI models is rapidly increasing the volume of synthetic data, with some projections suggesting that most available new data for training could…
AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs
Ruisi Zhang, Yifei Zhao, Neusha Javidnia +2
As on-device LLMs(e.g., Apple on-device Intelligence) are widely adopted to reduce network dependency, improve privacy, and enhance responsiveness, verifying the legitimacy of mode…
MergeGuard: Efficient Thwarting of Trojan Attacks in Machine Learning Models
Soheil Zibakhsh Shabgahi, Yaman Jandali, Farinaz Koushanfar
This paper proposes MergeGuard, a novel methodology for mitigation of AI Trojan attacks. Trojan attacks on AI models cause inputs embedded with triggers to be misclassified to an a…
Learning for Dynamic Combinatorial Optimization without Training Data
Yiqiao Liao, Farinaz Koushanfar, Parinaz Naghizadeh
We introduce DyCO-GNN, a novel unsupervised learning framework for Dynamic Combinatorial Optimization that requires no training data beyond the problem instance itself. DyCO-GNN le…
Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques
Neusha Javidnia, Bita Darvish Rouhani, Farinaz Koushanfar
Large language models (LLMs) have demonstrated exceptional capabilities in generating text, images, and video content. However, as context length grows, the computational cost of a…
Zero-Knowledge Proof Frameworks: A Systematic Survey
Nojan Sheybani, Anees Ahmed, Michel Kinsy +1
Zero-Knowledge Proofs (ZKPs) are a cryptographic primitive that allows a prover to demonstrate knowledge of a secret value to a verifier without revealing anything about the secret…
DROP: Poison Dilution via Knowledge Distillation for Federated Learning
Georgios Syros, Anshuman Suri, Farinaz Koushanfar +2
Federated Learning is vulnerable to adversarial manipulation, where malicious clients can inject poisoned updates to influence the global model's behavior. While existing defense m…
Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign
Ruisi Zhang, Neusha Javidnia, Nojan Sheybani +1
This paper introduces RoSeMary, the first-of-its-kind ML/Crypto codesign watermarking framework that regulates LLM-generated code to avoid intellectual property rights violations a…
Gotta Hash 'Em All! Speeding Up Hash Functions for Zero-Knowledge Proof Applications
Nojan Sheybani, Tengkai Gong, Anees Ahmed +3
Collision-resistant cryptographic hash functions (CRHs) are crucial for security, particularly for message authentication in Zero-knowledge Proof (ZKP) applications. However, tradi…
ICtoken: An NFT for Hardware IP Protection
Shashank Balla, Yiming Zhao, Farinaz Koushanfar
Protecting integrated circuits (ICs) from piracy and theft throughout their lifecycle is a persistent and complex challenge. In order to safeguard against illicit piracy attacks, t…
AMAZE: Accelerated MiMC Hardware Architecture for Zero-Knowledge Applications on the Edge
Anees Ahmed, Nojan Sheybani, Davi Moreno +4
Collision-resistant, cryptographic hash (CRH) functions have long been an integral part of providing security and privacy in modern systems. Certain constructions of zero-knowledge…
Trojan Cleansing with Neural Collapse
Xihe Gu, Greg Fields, Yaman Jandali +2
Trojan attacks are sophisticated training-time attacks on neural networks that embed backdoor triggers which force the network to produce a specific output on any input which inclu…
EveGuard: Defeating Vibration-based Side-Channel Eavesdropping with Audio Adversarial Perturbations
Jung-Woo Chang, Ke Sun, David Xia +2
Vibrometry-based side channels pose a significant privacy risk, exploiting sensors like mmWave radars, light sensors, and accelerometers to detect vibrations from sound sources or…