Search Results for author:
Found 23 papers, 6 papers with code
SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)
Split Learning (SL) is a distributed deep learning approach enabling multiple clients and a server to collaboratively train and infer on a shared deep neural network (DNN) without requiring clients to share their private local data.
Beyond Random Inputs: A Novel ML-Based Hardware Fuzzing
ChatFuzz achieves condition coverage rate of 75% in just 52 minutes compared to a state-of-the-art fuzzer, which requires a lengthy 30-hour window to reach a similar condition coverage.
One for All and All for One: GNN-based Control-Flow Attestation for Embedded Devices
The core intuition behind RAGE is to exploit the correspondence between execution trace, execution graph, and execution embeddings to eliminate the unrealistic requirement of having access to a complete CFG.
DeepEclipse: How to Break White-Box DNN-Watermarking Schemes
Deep Learning (DL) models have become crucial in digital transformation, thus raising concerns about their intellectual property rights.
FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning
Existing defenses against poisoning attacks in FL have several limitations, such as relying on specific assumptions about attack types and strategies or data distributions or not sufficiently robust against advanced injection techniques and strategies and simultaneously maintaining the utility of the aggregated model.
DEMASQ: Unmasking the ChatGPT Wordsmith
The potential misuse of ChatGPT and other Large Language Models (LLMs) has raised concerns regarding the dissemination of false information, plagiarism, academic dishonesty, and fraudulent activities.
To ChatGPT, or not to ChatGPT: That is the question!
The dataset serves as a reference to assess the performance of various techniques in detecting ChatGPT-generated content.
ARGUS: Context-Based Detection of Stealthy IoT Infiltration Attacks
ARGUS monitors the contextual setting based on the state and actions of IoT devices in the environment.
BayBFed: Bayesian Backdoor Defense for Federated Learning
However, as these approaches directly operate on client updates, their effectiveness depends on factors such as clients' data distribution or the adversary's attack strategies.
Follow Us and Become Famous! Insights and Guidelines From Instagram Engagement Mechanisms
Thanks to our interpretable approaches, we conclude by outlining guidelines for creating successful posts.
CrowdGuard: Federated Backdoor Detection in Federated Learning
However, FL is susceptible to backdoor (or targeted poisoning) attacks.
DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection
Using these techniques, DeepSight can identify suspicious model updates.
FakeWake: Understanding and Mitigating Fake Wake-up Words of Voice Assistants
In the area of Internet of Things (IoT) voice assistants have become an important interface to operate smart speakers, smartphones, and even automobiles.
BAFFLE: TOWARDS RESOLVING FEDERATED LEARNING’S DILEMMA - THWARTING BACKDOOR AND INFERENCE ATTACKS
Recently, federated learning (FL) has been subject to both security and privacy attacks posing a dilemmatic challenge on the underlying algorithmic designs: On the one hand, FL is shown to be vulnerable to backdoor attacks that stealthily manipulate the global model output using malicious model updates, and on the other hand, FL is shown vulnerable to inference attacks by a malicious aggregator inferring information about clients’ data from their model updates.
Trustworthy AI Inference Systems: An Industry Research View
Additionally, such systems should also use Privacy-Enhancing Technologies (PETs) to protect customers' data at any time.
V0LTpwn: Attacking x86 Processor Integrity from Software
We present V0LTpwn, a novel hardware-oriented but software-controlled attack that affects the integrity of computation in virtually any execution mode on modern x86 processors.
Cryptography and Security
Peek-a-Boo: I see your smart home activities, even encrypted!
It is realized utilizing state-of-the-art machine-learning approaches for detecting and identifying particular types of IoT devices, their actions, states, and ongoing user activities in a cascading style by only observing passively the wireless traffic from smart home devices.
Cryptography and Security
DIoT: A Self-learning System for Detecting Compromised IoT Devices
Consequently, DIoT can cope with the emergence of new device types as well as new attacks.
Cryptography and Security
Breaking Fitness Records without Moving: Reverse Engineering and Spoofing Fitbit
In this paper, we provide an in-depth security analysis of the operation of fitness trackers commercialized by Fitbit, the wearables market leader.
Cryptography and Security
Modeling Attack Resilient Reconfigurable Latent Obfuscation Technique for PUF based Lightweight Authentication
Physical unclonable functions (PUFs), as hardware security primitives, exploit manufacturing randomness to extract hardware instance-specific secrets.
Cryptography and Security
HardIDX: Practical and Secure Index with SGX
Software-based approaches for search over encrypted data are still either challenged by lack of proper, low-leakage encryption or slow performance.
Cryptography and Security
IoT Sentinel: Automated Device-Type Identification for Security Enforcement in IoT
In this paper, we present IOT SENTINEL, a system capable of automatically identifying the types of devices being connected to an IoT network and enabling enforcement of rules for constraining the communications of vulnerable devices so as to minimize damage resulting from their compromise.
Cryptography and Security
C-FLAT: Control-FLow ATtestation for Embedded Systems Software
Remote attestation is a crucial security service particularly relevant to increasingly popular IoT (and other embedded) devices.
Cryptography and Security
