ML-driven Malware that Targets AV Safety

2020-04-24 · Saurabh Jha, Shengkun Cui, Subho S. Banerjee, Timothy Tsai, Zbigniew Kalbarczyk, Ravi Iyer

Ensuring the safety of autonomous vehicles (AVs) is critical for their mass deployment and public adoption. However, security attacks that violate safety constraints and cause accidents are a significant deterrent to achieving public trust in AVs, and that hinders a vendor's ability to deploy AVs. Creating a security hazard that results in a severe safety compromise (for example, an accident) is compelling from an attacker's perspective. In this paper, we introduce an attack model, a method to deploy the attack in the form of smart malware, and an experimental evaluation of its impact on production-grade autonomous driving software. We find that determining the time interval during which to launch the attack is{ critically} important for causing safety hazards (such as collisions) with a high degree of success. For example, the smart malware caused 33X more forced emergency braking than random attacks did, and accidents in 52.6% of the driving simulations.

📄 PDF Abstract BibTeX arXiv:2004.13004

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Driving Autonomous Vehicles

AI Agents Enable Adaptive Computer Worms

2026-06-02 · Jonas Guan, Tom Blanchard, Hanna Foerster, Hengrui Jia 외 arxiv

A computer worm is malware that spreads on a network by replicating itself from one machine to another. Traditional worms, like WannaCry, exploited predetermined vulnerabilities, and their spread can be halted by patchin…

ALOHA: Auxiliary Loss Optimization for Hypothesis Augmentation

2019-03-13 · Ethan M. Rudd, Felipe N. Ducau, Cody Wild, Konstantin Berlin 외

Malware detection is a popular application of Machine Learning for Information Security (ML-Sec), in which an ML classifier is trained to predict whether a given file is malware or benignware. Parameters of this classifi…

Attribute Malware Detection TAG

Flytxt\_NTNU at SemEval-2018 Task 8: Identifying and Classifying Malware Text Using Conditional Random Fields and Na\"\ive Bayes Classifiers

2018-06-01 · SEMEVAL 2018 6 · Utpal Kumar Sikdar, Biswanath Barik, Bj{\"o}rn Gamb{\"a}ck

Cybersecurity risks such as malware threaten the personal safety of users, but to identify malware text is a major challenge. The paper proposes a supervised learning approach to identifying malware sentences given a doc…

Synthetic Cancer -- Augmenting Worms with LLMs

2024-06-27 · Benjamin Zimmerman, David Zollikofer

With increasingly sophisticated large language models (LLMs), the potential for abuse rises drastically. As a submission to the Swiss AI Safety Prize, we present a novel type of metamorphic malware leveraging LLMs for tw…

Data Augmentation Based Malware Detection using Convolutional Neural Networks

2020-10-05 · Ferhat Ozgur Catak, Javed Ahmed, Kevser Sahinbas, Zahid Hussain Khand

Recently, cyber-attacks have been extensively seen due to the everlasting increase of malware in the cyber world. These attacks cause irreversible damage not only to end-users but also to corporate computer systems. Rans…

Data Augmentation Image Augmentation Image Generation Malware Detection+1