47 citations · 172 across the 92 of their papers we have counts for
21 papers · 1 filter
How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security Evaluation
Kimberly Milner, Minghao Shao, Nanda Rani +8
Capture-the-Flag (CTF) benchmarks are widely used to assess the offensive security capabilities of autonomous language-model agents. Evaluations rely on shallow binary judgments or…
Long-Term and Short-Term Transistor Aging in Deep Neural Networks: Impact and Mitigation
Alireza Sarmadi, Virinchi Roy Surabhi, Prashanth Krishnamurthy +3
Deep neural networks (DNNs) are used in a variety of real-world applications including, for example, image classification and speech recognition. The inference accuracy of DNN impl…
Safeguarding LLMs Against Misuse and AI-Driven Malware Using Steganographic Canaries
Md Raz, Venkata Sai Charan Putrevu, Meet Udeshi +3
AI-powered malware increasingly exploits cloud-hosted generative-AI services and large language models (LLMs) as analysis engines for reconnaissance and code generation. Simultaneo…
CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking
Nanda Rani, Kimberly Milner, Minghao Shao +9
Existing benchmarks for LLM-based offensive security agents use isolated, single-target setups with a known vulnerable service and fixed objective. They measure exploitation effect…
Binary Diff Summarization using Large Language Models
Meet Udeshi, Venkata Sai Charan Putrevu, Prashanth Krishnamurthy +4
Security of software supply chains is necessary to ensure that software updates do not contain maliciously injected code or introduce vulnerabilities that may compromise the integr…
Ransomware 3.0: Self-Composing and LLM-Orchestrated
Md Raz, Meet Udeshi, P. V. Sai Charan +3
Using automated reasoning, code synthesis, and contextual decision-making, we introduce a new threat that exploits large language models (LLMs) to autonomously plan, adapt, and exe…
SCAMPER -- Synchrophasor Covert chAnnel for Malicious and Protective ERrands
Prashanth Krishnamurthy, Ramesh Karri, Farshad Khorrami
We note that constituent fields (notably the fraction-of-seconds timestamp field) in the data payload structure of the synchrophasor communication protocol (IEEE C37.118 standard)…
An Orchestrated Sandbox for Side-Channel Analysis of Cyber-Physical Systems Malware
Meet Udeshi, Venkata Sai Charan Putrevu, Prashanth Krishnamurthy +2
Embedded devices powering cyber-physical systems (CPS) are increasingly internet-exposed, placing critical infrastructure under active threat. Dynamic analysis of embedded malware…
Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark
Minghao Shao, Nanda Rani, Kimberly Milner +9
Recent advances in LLM agentic systems have improved the automation of offensive security tasks, particularly for Capture the Flag (CTF) challenges. We systematically investigate t…
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Minghao Shao, Haoran Xi, Nanda Rani +9
Large Language Model (LLM) agents can automate cybersecurity tasks and can adapt to the evolving cybersecurity landscape without re-engineering. While LLM agents have demonstrated…
Enabling Deep Visibility into VxWorks-Based Embedded Controllers in Cyber-Physical Systems for Anomaly Detection
Prashanth Krishnamurthy, Ramesh Karri, Farshad Khorrami
We propose the DIVER (Defensive Implant for Visibility into Embedded Run-times) framework for real-time deep visibility into embedded control devices in cyber-physical systems (CPS…
Real-Time Multi-Modal Subcomponent-Level Measurements for Trustworthy System Monitoring and Malware Detection
Farshad Khorrami, Ramesh Karri, Prashanth Krishnamurthy
With increasingly sophisticated cyber-adversaries able to access a wider repertoire of mechanisms to implant malware such as ransomware, CPU/GPU keyloggers, and stealthy kernel roo…
SHIELD: A Host-Independent Framework for Ransomware Detection using Deep Filesystem Features
Md Raz, Venkata Sai Charan Putrevu, Prashanth Krishnamurthy +2
Ransomware's escalating sophistication necessitates tamper-resistant, off-host detection solutions that capture deep disk activity beyond the reach of a compromised operating syste…
SENTAUR: Security EnhaNced Trojan Assessment Using LLMs Against Undesirable Revisions
Jitendra Bhandari, Rajat Sadhukhan, Prashanth Krishnamurthy +2
A globally distributed IC supply chain brings risks due to untrusted third parties. The risks span inadvertent use of hardware Trojan (HT), inserted Intellectual Property (3P-IP) o…
NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
Minghao Shao, Sofija Jancheska, Meet Udeshi +10
Large Language Models (LLMs) are being deployed across various domains today. However, their capacity to solve Capture the Flag (CTF) challenges in cybersecurity has not been thoro…
OffRAMPS: An FPGA-based Intermediary for Analysis and Modification of Additive Manufacturing Control Systems
Jason Blocklove, Md Raz, Prithwish Basu Roy +4
Cybersecurity threats in Additive Manufacturing (AM) are an increasing concern as AM adoption continues to grow. AM is now being used for parts in the aerospace, transportation, an…
On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
Georg Pichler, Marco Romanelli, Divya Prakash Manivannan +3
We introduce a formal statistical definition for the problem of backdoor detection in machine learning systems and use it to analyze the feasibility of such problems, providing evi…
Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detection
Hao Fu, Prashanth Krishnamurthy, Siddharth Garg +1
This paper proposes a data-efficient detection method for deep neural networks against backdoor attacks under a black-box scenario. The proposed approach is motivated by the intuit…
REMaQE: Reverse Engineering Math Equations from Executables
Meet Udeshi, Prashanth Krishnamurthy, Hammond Pearce +2
Cybersecurity attacks on embedded devices for industrial control systems and cyber-physical systems may cause catastrophic physical damage as well as economic loss. This could be a…
ESAFE: Enterprise Security and Forensics at Scale
Bernard McShea, Kevin Wright, Denley Lam +7
Securing enterprise networks presents challenges in terms of both their size and distributed structure. Data required to detect and characterize malicious activities may be diffuse…
NNoculation: Catching BadNets in the Wild
Akshaj Kumar Veldanda, Kang Liu, Benjamin Tan +5
This paper proposes a novel two-stage defense (NNoculation) against backdoored neural networks (BadNets) that, repairs a BadNet both pre-deployment and online in response to backdo…