arXiv subjects

Sencun Zhu

Publications and source records attributed to Sencun Zhu.

At least 19 recordsLinked to original sources

arXiv2026

LLM-Based Penetration Testing in the Presence of Honeypots

Large language model (LLM) agents are increasingly employed for offensive cybersecurity tasks such as automated vulnerability discovery, reconnaissance, and penetration testing. This new capability also threatens one of the defender's most valuable tools: deception. Traditional honeypots rely on realism and obscurity to lure human or script-driven attackers into revealing tactics, techniques, and procedures (TTPs), but LLM-driven attackers can reason about heterogeneous artifacts and use the honeypot suspicion to guide target-selection decisions. We present a systematic study of honeypot-aware budget allocation for LLM attack agents. We formalize the attacker's problem as a budgeted decision process: an agent interacts with potential targets, consuming LLM execution budget during reconnaissance and exploitation, and must decide whether to (continue exploitation) or (skip) when honeypot suspicion arises. Our findings show that with the proposed detector-guided policy, LLM agent attackers can effectively allocate budget to compromise hosts in a host pool, highlighting the importance of dynamically allocating budget in a controlled mixed-host testbed. While defenses are beyond our present scope, we discuss implications for future adversarially resilient and adaptive honeypot design.

cs.CR↗

arXiv2026

Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses

Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage information, and context. While this has improved the agent's functionality and continuity across tasks, it has also introduced a new attack surface: the agent's own reasoning history. In this paper, we introduce the Forged Amplifying Rationale Memory Attack (FARMA), which poisons an agent's remembered reasoning rather than its factual knowledge. It inserts forged reasoning traces using evasive language that bypasses keyword-based defenses, then amplifies them through self-referential reinforcement that defeats consensus-based defenses. To address FARMA, we introduce SENTINEL, a layered defense pipeline to detect forged reasoning entries. Its central component is the Reasoning Guard that structurally analyzes candidate entries for forgery using five weighted signals. We evaluate FARMA and SENTINEL across multiple agents and different LLM models with 50 trials and show that FARMA achieves an attack success rate of up to 100% under baseline conditions and is capable of defeating defense mechanisms like keyword filter and A-MemGuard. Our evaluation also shows that SENTINEL reduces FARMA's attack success rate to as low as 0% with no false positives observed across 326 benign agent traces. Our work demonstrates the need to protect not only an agent's retrieved content but also the integrity of its reasoning history.

cs.CR↗

arXiv2025

How to Backdoor Image Knowledge Distillation

Knowledge distillation is widely used to transfer behavior from a large teacher model to a smaller student. It is often assumed to be safe when the teacher is clean, because classic backdoor attacks rely on poisoned labels and triggers in supervised training, whereas distillation trains the student to match a teacher's outputs. We show that this assumption can fail when the distillation dataset itself is poisoned. Our attack injects triggered and manipulated images that a clean teacher already predicts as an attacker chosen target label, which causes the student to learn a backdoor even though the teacher remains unaffected. We evaluate this threat across multiple manipulation strategies, including targeted adversarial perturbations and targeted GAN based class transitions, and study how distillation settings influence both accuracy and attack success. We show that the attack remains effective even at a 10% poisoning rates. The results demonstrate that a clean teacher alone is not a sufficient safeguard: poisoned distillation data can produce a strongly backdoored student while maintaining competitive performance on clean images. These findings show that the integrity and provenance of distillation data are part of the security boundary of data intensive KD pipelines, even when the teacher itself is trusted.

cs.CR↗

arXiv2025

Prompting Forgetting: Unlearning in GANs via Textual Guidance

State-of-the-art generative models exhibit powerful image-generation capabilities, introducing various ethical and legal challenges to service providers hosting these models. Consequently, Content Removal Techniques (CRTs) have emerged as a growing area of research to control outputs without full-scale retraining. Recent work has explored the use of Machine Unlearning in generative models to address content removal. However, the focus of such research has been on diffusion models, and unlearning in Generative Adversarial Networks (GANs) has remained largely unexplored. We address this gap by proposing Text-to-Unlearn, a novel framework that selectively unlearns concepts from pre-trained GANs using only text prompts, enabling feature unlearning, identity unlearning, and fine-grained tasks like expression and multi-attribute removal in models trained on human faces. Leveraging natural language descriptions, our approach guides the unlearning process without requiring additional datasets or supervised fine-tuning, offering a scalable and efficient solution. To evaluate its effectiveness, we introduce an automatic unlearning assessment method adapted from state-of-the-art image-text alignment metrics, providing a comprehensive analysis of the unlearning methodology. To our knowledge, Text-to-Unlearn is the first cross-modal unlearning framework for GANs, representing a flexible and efficient advancement in managing generative model behavior.

cs.LG↗

arXiv2024

The Illusion of Anonymity: Uncovering the Impact of User Actions on Privacy in Web3 Social Ecosystems

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. Nonetheless, this progress is shadowed by potential privacy concessions, especially as these platforms frequently merge with existing Web2.0 social media accounts, amplifying data privacy risks for users. In this study, we investigate the nuanced dynamics between user engagement on Web3 social platforms and the consequent privacy concerns. We scrutinize the widespread phenomenon of fabricated activities, which encompasses the establishment of bogus accounts aimed at mimicking popularity and the deliberate distortion of social interactions by some individuals to gain financial rewards. Such deceptive maneuvers not only distort the true measure of the active user base but also amplify privacy threats for all members of the user community. We also find that, notwithstanding their attempts to limit social exposure, users remain entangled in privacy vulnerabilities. The actions of those highly engaged users, albeit often a minority group, can inadvertently breach the privacy of the larger collective. By casting light on the delicate interplay between user engagement, financial motives, and privacy issues, we offer a comprehensive examination of the intrinsic challenges and hazards present in the Web3 social milieu. We highlight the urgent need for more stringent privacy measures and ethical protocols to navigate the complex web of social exchanges and financial ambitions in the rapidly evolving Web3.

cs.CR↗

arXiv2023

Learning to Backdoor Federated Learning

In a federated learning (FL) system, malicious participants can easily embed backdoors into the aggregated model while maintaining the model's performance on the main task. To this end, various defenses, including training stage aggregation-based defenses and post-training mitigation defenses, have been proposed recently. While these defenses obtain reasonable performance against existing backdoor attacks, which are mainly heuristics based, we show that they are insufficient in the face of more advanced attacks. In particular, we propose a general reinforcement learning-based backdoor attack framework where the attacker first trains a (non-myopic) attack policy using a simulator built upon its local data and common knowledge on the FL system, which is then applied during actual FL training. Our attack framework is both adaptive and flexible and achieves strong attack performance and durability even under state-of-the-art defenses.

cs.LG↗

arXiv2023

HoneyIoT: Adaptive High-Interaction Honeypot for IoT Devices Through Reinforcement Learning

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 is to deploy IoT honeypot systems, which can collect attack information and reveal the methods and strategies used by attackers. However, building high-interaction IoT honeypots is challenging due to the heterogeneity of IoT devices. Vulnerabilities in IoT devices typically depend on specific device types or firmware versions, which encourages attackers to perform pre-attack checks to gather device information before launching attacks. Moreover, conventional honeypots are easily detected because their replying logic differs from that of the IoT devices they try to mimic. To address these problems, we develop an adaptive high-interaction honeypot for IoT devices, called HoneyIoT. We first build a real device based attack trace collection system to learn how attackers interact with IoT devices. We then model the attack behavior through markov decision process and leverage reinforcement learning techniques to learn the best responses to engage attackers based on the attack trace. We also use differential analysis techniques to mutate response values in some fields to generate high-fidelity responses. HoneyIoT has been deployed on the public Internet. Experimental results show that HoneyIoT can effectively bypass the pre-attack checks and mislead the attackers into uploading malware. Furthermore, HoneyIoT is covert against widely used reconnaissance and honeypot detection tools.

cs.CR↗

arXiv2022

Generating Practical Adversarial Network Traffic Flows Using NIDSGAN

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 basis for NIDS decision making, where models are tuned to reduce false alarms, increase detection rates, and detect known and unknown attacks. At the same time, ML models have been found to be vulnerable to adversarial examples that undermine the downstream task. In this work, we ask the practical question of whether real-world ML-based NIDS can be circumvented by crafted adversarial flows, and if so, how can they be created. We develop the generative adversarial network (GAN)-based attack algorithm NIDSGAN and evaluate its effectiveness against realistic ML-based NIDS. Two main challenges arise for generating adversarial network traffic flows: (1) the network features must obey the constraints of the domain (i.e., represent realistic network behavior), and (2) the adversary must learn the decision behavior of the target NIDS without knowing its model internals (e.g., architecture and meta-parameters) and training data. Despite these challenges, the NIDSGAN algorithm generates highly realistic adversarial traffic flows that evade ML-based NIDS. We evaluate our attack algorithm against two state-of-the-art DNN-based NIDS in whitebox, blackbox, and restricted-blackbox threat models and achieve success rates which are on average 99%, 85%, and 70%, respectively. We also show that our attack algorithm can evade NIDS based on classical ML models including logistic regression, SVM, decision trees and KNNs, with a success rate of 70% on average. Our results demonstrate that deploying ML-based NIDS without careful defensive strategies against adversarial flows may (and arguably likely will) lead to future compromises.

cs.CR↗

arXiv2022

Federated Unlearning with Knowledge Distillation

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 trained model may memorize certain information about the training data. With the recent legislation on right to be forgotten, it is crucially essential for the FL model to possess the ability to forget what it has learned from each client. We propose a novel federated unlearning method to eliminate a client's contribution by subtracting the accumulated historical updates from the model and leveraging the knowledge distillation method to restore the model's performance without using any data from the clients. This method does not have any restrictions on the type of neural networks and does not rely on clients' participation, so it is practical and efficient in the FL system. We further introduce backdoor attacks in the training process to help evaluate the unlearning effect. Experiments on three canonical datasets demonstrate the effectiveness and efficiency of our method.

cs.LG↗

arXiv2021

AppQ: Warm-starting App Recommendation Based on View Graphs

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) user feedback, suffering from the classic cold-start problem. How to quickly identify and then recommend new apps of high quality is a challenging issue. Here, a fundamental requirement is the capability to accurately measure an app's quality based on its inborn features, rather than user-generated features. Since users obtain first-hand experience of an app by interacting with its views, we speculate that the inborn features are largely related to the visual quality of individual views in an app and the ways the views switch to one another. In this work, we propose AppQ, a novel app quality grading and recommendation system that extracts inborn features of apps based on app source code. In particular, AppQ works in parallel to perform code analysis to extract app-level features as well as dynamic analysis to capture view-level layout hierarchy and the switching among views. Each app is then expressed as an attributed view graph, which is converted into a vector and fed to classifiers for recognizing its quality classes. Our evaluation with an app dataset from Google Play reports that AppQ achieves the best performance with accuracy of 85.0\%. This shows a lot of promise to warm-start app grading and recommendation systems with AppQ.

cs.IR↗

arXiv2021

Let Your Camera See for You: A Novel Two-Factor Authentication Method against Real-Time Phishing Attacks

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 vulnerable to carefully designed phishing attacks, and some even request special hardware, which limits their wide deployment. Recently, real-time phishing (RTP) has made the situation even worse because an adversary can effortlessly establish a phishing website replicating a target website without any background of the web page design technique. Traditional 2FA can be easily bypassed by such RTP attacks. In this work, we propose a novel 2FA system to counter RTP attacks. The main idea is to request a user to take a photo of the web browser with the domain name in the address bar as the 2nd authentication factor. The web server side extracts the domain name information based on Optical Character Recognition (OCR), and then determines if the user is visiting this website or a fake one, thus defeating the RTP attacks where an adversary must set up a fake website with a different domain. We prototyped our system and evaluated its performance in various environments. The results showed that PhotoAuth is an effective technique with good scalability. We also showed that compared to other 2FA systems, PhotoAuth has several advantages, especially no special hardware or software support is needed on the client side except a phone, making it readily deployable.

cs.CR↗

arXiv2021

Mitigating Backdoor Attacks in Federated Learning

Malicious clients can attack federated learning systems using malicious data, including backdoor samples, during the training phase. The compromised global model will perform well on the validation dataset designed for the task, but a small subset of data with backdoor patterns may trigger the model to make a wrong prediction. There has been an arms race between attackers who tried to conceal attacks and defenders who tried to detect attacks during the aggregation stage of training on the server-side. In this work, we propose a new and effective method to mitigate backdoor attacks after the training phase. Specifically, we design a federated pruning method to remove redundant neurons in the network and then adjust the model's extreme weight values. Our experiments conducted on distributed Fashion-MNIST show that our method can reduce the average attack success rate from 99.7% to 1.9% with a 5.5% loss of test accuracy on the validation dataset. To minimize the pruning influence on test accuracy, we can fine-tune after pruning, and the attack success rate drops to 6.4%, with only a 1.7% loss of test accuracy. Further experiments under Distributed Backdoor Attacks on CIFAR-10 also show promising results that the average attack success rate drops more than 70% with less than 2% loss of test accuracy on the validation dataset.

cs.CR↗

arXiv2020

Time-Window Group-Correlation Support vs. Individual Features: A Detection of Abnormal Users

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 follow past habitual patterns. Most existing approaches typically build models by reconstructing single-day and individual-user behaviors. However, without capturing long-term signals and group-correlation signals, the models cannot identify low-signal yet long-lasting threats, and will wrongly report many normal users as anomalies on busy days, which, in turn, lead to high false positive rate. In this paper, we propose ACOBE, an Anomaly detection method based on COmpound BEhavior, which takes into consideration long-term patterns and group behaviors. ACOBE leverages a novel behavior representation and an ensemble of deep autoencoders and produces an ordered investigation list. Our evaluation shows that ACOBE outperforms prior work by a large margin in terms of precision and recall, and our case study demonstrates that ACOBE is applicable in practice for cyberattack detection.

cs.LG↗

arXiv2020

Recomposition vs. Prediction: A Novel Anomaly Detection for Discrete Events Based On Autoencoder

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 learning upon engineered features, most recent work has started to resolve this challenge by applying deep learning methodology to abstraction of discrete event entries. Inspired by natural language processing, LSTM-based anomaly detection models were proposed. They try to predict upcoming events, and raise an anomaly alert when a prediction fails to meet a certain criterion. However, such a predict-next-event methodology has a fundamental limitation: event predictions may not be able to fully exploit the distinctive characteristics of sequences. This limitation leads to high false positives (FPs) and high false negatives (FNs). It is also critical to examine the structure of sequences and the bi-directional causality among individual events. To this end, we propose a new methodology: Recomposing event sequences as anomaly detection. We propose DabLog, a Deep Autoencoder-Based anomaly detection method for discrete event Logs. The fundamental difference is that, rather than predicting upcoming events, our approach determines whether a sequence is normal or abnormal by analyzing (encoding) and reconstructing (decoding) the given sequence. Our evaluation results show that our new methodology can significantly reduce the numbers of FPs and FNs, hence achieving a higher $F_1$ score.

cs.LG↗

arXiv2020

Toward A Network-Assisted Approach for Effective Ransomware Detection

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 desktops unless they pay the ransom to the attackers. By the end of 2019, ransomware attack had caused more than 10 billion dollars of financial loss to enterprises and individuals. In this work, we propose Network-Assisted Approach (NAA), which contains effective local detection and network-level detection mechanisms, to help users determine whether a machine has been infected by ransomware. To evaluate its performance, we built 100 containers in Docker to simulate network scenarios. A hybrid ransomware sample which is close to real-world ransomware is deployed on stimulative infected machines. The experiment results show that our network-level detection mechanisms are separately applicable to WAN and LAN environments for ransomware detection.

cs.CR↗

arXiv2020

"Are you home alone?" "Yes" Disclosing Security and Privacy Vulnerabilities in Alexa Skills

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. These skills, though useful, have also introduced new security and privacy challenges. Prior work has verified that Alexa is vulnerable to multiple types of voice attacks, but the security and privacy risk of using skills has not been fully investigated. In this work, we study an adversary model that covers three severe privacy-related vulnerabilities, namely,over-privileged resource access, hidden code-manipulation and hidden content-manipulation. By exploiting these vulnerabilities, malicious skills can not only bypass the security tests in the vetting process, but also surreptitiously change their original functions in an attempt to steal users' personal information. What makes the situation even worse is that the attacks can be extended from virtual networks to the physical world. We systematically study the security issues from the feasibility and implementation of the attacks to the design of countermeasures. We also made a comprehensive survey study of 33,744 skills in Alex Skills Store.

cs.CR↗

arXiv2019

A Lightweight Blockchain-based Privacy Protection for Smart Surveillance at the Edge

Witnessing the increasingly pervasive deployment of security video surveillance systems(VSS), more and more individuals have become concerned with the issues of privacy violations. While the majority of the public have a favorable view of surveillance in terms of crime deterrence, individuals do not accept the invasive monitoring of their private life. To date, however, there is not a lightweight and secure privacy-preserving solution for video surveillance systems. The recent success of blockchain (BC) technologies and their applications in the Internet of Things (IoT) shed a light on this challenging issue. In this paper, we propose a Lightweight, Blockchain-based Privacy protection (Lib-Pri) scheme for surveillance cameras at the edge. It enables the VSS to perform surveillance without compromising the privacy of people captured in the videos. The Lib-Pri system transforms the deployed VSS into a system that functions as a federated blockchain network capable of carrying out integrity checking, blurring keys management, feature sharing, and video access sanctioning. The policy-based enforcement of privacy measures is carried out at the edge devices for real-time video analytics without cluttering the network.

cs.DC↗

arXiv2019

No Peeking through My Windows: Conserving Privacy in Personal Drones

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 in various sizes and are designed for a multitude of purposes. Nowadays many people have small-sized personal drones for entertainment, filming, or transporting items from one place to another. However, personal drones lack a privacy-preserving mechanism. While in mission, drones often trespass into the personal territories of other people and capture photos or videos through windows without their knowledge and consent. They may also capture video or pictures of people walking, sitting, or doing private things within the drones' reach in clear form without their go permission. This could potentially invade people's personal privacy. This paper, therefore, proposes a lightweight privacy-preserving-by-design method that prevents drones from peeking through windows of houses and capturing people doing private things at home. It is a fast window object detection and scrambling technology built based on image-enhancing, morphological transformation, segmentation and contouring processes (MASP). Besides, a chaotic scrambling technique is incorporated into it for privacy purpose. Hence, this mechanism detects window objects in every image or frame of a real-time video and masks them chaotically to protect the privacy of people. The experimental results validated that the proposed MASP method is lightweight and suitable to be employed in drones, considered as edge devices.

cs.CR↗