19 citations · 47 across the 12 of their papers we have counts for
12 papers
AMEND: Audited Margins Enable Nonblocking Drops in GPU-PIM LLM Decoding
Zuxiong Tan, Will Wei-Jen Wang, Wei Shao +3
Autoregressive large language model (LLM) decoding re-reads a growing key-value (KV) cache at every step, so long-context attention is bound by graphics processing unit (GPU) memor…
Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents
Wei Shao, Chongzhou Fang, Zuxiong Tan +4
Long-horizon security LLM agents must carry information and decisions across many dependent interactions, where later actions often depend on services, state, or access discovered…
SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation
Ali Karkehabadi, Jamshid Hassanpour, Houman Homayoun +1
Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meanin…
Transformers for Secure Hardware Systems: Applications, Challenges, and Outlook
Banafsheh Saber Latibari, Najmeh Nazari, Avesta Sasan +4
The rise of hardware-level security threats, such as side-channel attacks, hardware Trojans, and firmware vulnerabilities, demands advanced detection mechanisms that are more intel…
FFCL: Forward-Forward Net with Cortical Loops, Training and Inference on Edge Without Backpropagation
Ali Karkehabadi, Houman Homayoun, Avesta Sasan
The Forward-Forward Learning (FFL) algorithm is a recently proposed solution for training neural networks without needing memory-intensive backpropagation. During training, labels…
Automated Hardware Logic Obfuscation Framework Using GPT
Banafsheh Saber Latibari, Sujan Ghimire, Muhtasim Alam Chowdhury +5
Obfuscation stands as a promising solution for safeguarding hardware intellectual property (IP) against a spectrum of threats including reverse engineering, IP piracy, and tamperin…
Generative AI-Based Effective Malware Detection for Embedded Computing Systems
Sreenitha Kasarapu, Sanket Shukla, Rakibul Hassan +3
One of the pivotal security threats for the embedded computing systems is malicious software a.k.a malware. With efficiency and efficacy, Machine Learning (ML) has been widely adop…
Gotcha! I Know What You are Doing on the FPGA Cloud: Fingerprinting Co-Located Cloud FPGA Accelerators via Measuring Communication Links
Chongzhou Fang, Ning Miao, Han Wang +5
In recent decades, due to the emerging requirements of computation acceleration, cloud FPGAs have become popular in public clouds. Major cloud service providers, e.g. AWS and Micro…
Adaptive-Gravity: A Defense Against Adversarial Samples
Ali Mirzaeian, Zhi Tian, Sai Manoj P D +4
This paper presents a novel model training solution, denoted as Adaptive-Gravity, for enhancing the robustness of deep neural network classifiers against adversarial examples. We c…
Repttack: Exploiting Cloud Schedulers to Guide Co-Location Attacks
Chongzhou Fang, Han Wang, Najmeh Nazari +5
Cloud computing paradigms have emerged as a major facility to store and process the massive data produced by various business units, public organizations, Internet-of-Things, and c…
NNgSAT: Neural Network guided SAT Attack on Logic Locked Complex Structures
Kimia Zamiri Azar, Hadi Mardani Kamali, Houman Homayoun +1
The globalization of the IC supply chain has raised many security threats, especially when untrusted parties are involved. This has created a demand for a dependable logic obfuscat…
InterLock: An Intercorrelated Logic and Routing Locking
Hadi Mardani Kamali, Kimia Zamiri Azar, Houman Homayoun +1
In this paper, we propose a canonical prune-and-SAT (CP&SAT) attack for breaking state-of-the-art routing-based obfuscation techniques. In the CP&SAT attack, we first encode the ke…