105 citations · 251 across the 19 of their papers we have counts for
21 papers
Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks
Neeraj Karamchandani, Piyush Nagasubramaniam, Xinhong Xie +2
Security benchmarks for LLM-based agents often report the attack success rate (ASR) as a measure of model robustness and use these scores to compare different models and defense me…
LLM-Based Penetration Testing in the Presence of Honeypots
Xinhong Xie, Piyush Nagasubramaniam, Neeraj Karamchandani +1
Large language model (LLM) agents are increasingly employed for offensive cybersecurity tasks such as automated vulnerability discovery, reconnaissance, and penetration testing. Th…
Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses
Neeraj Karamchandani, Piyush Nagasubramaniam, Sencun Zhu +1
Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage information, and context. While this ha…
Anatomy of the simplest renormalon
Marcos Marino
Perhaps the simplest IR renormalon occurs in the ground state energy of a superrenormalizable model, the scalar theory in two dimensions with a quartic potential and negativ…
Prompting Forgetting: Unlearning in GANs via Textual Guidance
Piyush Nagasubramaniam, Neeraj Karamchandani, Chen Wu +1
State-of-the-art generative models exhibit powerful image-generation capabilities, introducing various ethical and legal challenges to service providers hosting these models. Conse…
The Illusion of Anonymity: Uncovering the Impact of User Actions on Privacy in Web3 Social Ecosystems
Bin Wang, Tianjian Liu, Wenqi Wang +6
The rise of Web3 social ecosystems signifies the dawn of a new chapter in digital interaction, offering significant prospects for user engagement and financial advancement. Nonethe…
HoneyIoT: Adaptive High-Interaction Honeypot for IoT Devices Through Reinforcement Learning
Chongqi Guan, Heting Liu, Guohong Cao +2
As IoT devices are becoming widely deployed, there exist many threats to IoT-based systems due to their inherent vulnerabilities. One effective approach to improving IoT security i…
Generating Practical Adversarial Network Traffic Flows Using NIDSGAN
Bolor-Erdene Zolbayar, Ryan Sheatsley, Patrick McDaniel +4
Network intrusion detection systems (NIDS) are an essential defense for computer networks and the hosts within them. Machine learning (ML) nowadays predominantly serves as the basi…
Federated Unlearning with Knowledge Distillation
Chen Wu, Sencun Zhu, Prasenjit Mitra
Federated Learning (FL) is designed to protect the data privacy of each client during the training process by transmitting only models instead of the original data. However, the tr…
AppQ: Warm-starting App Recommendation Based on View Graphs
Dan Su, Jiqiang Liu, Sencun Zhu +3
Current app ranking and recommendation systems are mainly based on user-generated information, e.g., number of downloads and ratings. However, new apps often have few (or even no)…
Let Your Camera See for You: A Novel Two-Factor Authentication Method against Real-Time Phishing Attacks
Yuanyi Sun, Sencun Zhu, Yao Zhao +1
Today, two-factor authentication (2FA) is a widely implemented mechanism to counter phishing attacks. Although much effort has been investigated in 2FA, most 2FA systems are still…
Recomposition vs. Prediction: A Novel Anomaly Detection for Discrete Events Based On Autoencoder
Lun-Pin Yuan, Peng Liu, Sencun Zhu
One of the most challenging problems in the field of intrusion detection is anomaly detection for discrete event logs. While most earlier work focused on applying unsupervised lear…
Time-Window Group-Correlation Support vs. Individual Features: A Detection of Abnormal Users
Lun-Pin Yuan, Euijin Choo, Ting Yu +2
Autoencoder-based anomaly detection methods have been used in identifying anomalous users from large-scale enterprise logs with the assumption that adversarial activities do not fo…
Mitigating Backdoor Attacks in Federated Learning
Chen Wu, Xian Yang, Sencun Zhu +1
Malicious clients can attack federated learning systems using malicious data, including backdoor samples, during the training phase. The compromised global model will perform well…
"Are you home alone?" "Yes" Disclosing Security and Privacy Vulnerabilities in Alexa Skills
Dan Su, Jiqiang Liu, Sencun Zhu +2
The home voice assistants such as Amazon Alexa have become increasingly popular due to many interesting voice-activated services provided through special applications called skills…
Toward A Network-Assisted Approach for Effective Ransomware Detection
Tianrou Xia, Yuanyi Sun, Sencun Zhu +2
Ransomware is a kind of malware using cryptographic mechanisms to prevent victims from normal use of their computers. As a result, victims lose the access to their files and deskto…
A Lightweight Blockchain-based Privacy Protection for Smart Surveillance at the Edge
Alem Fitwi, Yu Chen, Sencun Zhu
Witnessing the increasingly pervasive deployment of security video surveillance systems(VSS), more and more individuals have become concerned with the issues of privacy violations.…
No Peeking through My Windows: Conserving Privacy in Personal Drones
Alem Fitwi, Yu Chen, Sencun Zhu
The drone technology has been increasingly used by many tech-savvy consumers, a number of defense companies, hobbyists and enthusiasts during the last ten years. Drones often come…
A Study on Smart Online Frame Forging Attacks against Video Surveillance System
Deeraj Nagothu, Jacob Schwell, Yu Chen +2
Video Surveillance Systems (VSS) have become an essential infrastructural element of smart cities by increasing public safety and countering criminal activities. A VSS is normally…
Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation
Cong Liao, Haoti Zhong, Anna Squicciarini +2
Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become i…
Keeping Context In Mind: Automating Mobile App Access Control with User Interface Inspection
Hao Fu, Zizhan Zheng, Sencun Zhu +1
Recent studies observe that app foreground is the most striking component that influences the access control decisions in mobile platform, as users tend to deny permission requests…