The Threat of Offensive AI to Organizations

Mirsky, Yisroel; Demontis, Ambra; Kotak, Jaidip; Shankar, Ram; Deng, Gelei; Liu, Yang; Zhang, Xiangyu; Pintor, Maura; Lee, Wenke; Elovici, Yuval; Biggio, Battista

doi:10.1016/j.cose.2022.103006

Cited by 22 publications

(20 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More deepfakes in the wild will have a knock-on effect. Adversaries will have more opportunities to scale their operations, particularly for misinformation such as impersonations and spear phishing (Mirsky et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Warning: Humans Cannot Reliably Detect Speech Deepfakes

Mai¹,

Bray²,

Davies³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

“…Understanding the extent of these threats is critical. Multiple studies deem other uses of speech deepfakes as more concerning, such as misleading people through voice impersonations (Caldwell et al, 2020;Mirsky et al, 2022).…”

mentioning

confidence: 99%

Warning: Humans Cannot Reliably Detect Speech Deepfakes

Mai¹,

Bray²,

Davies³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…There are also many papers on the survey and taxonomy of machine learning security (e.g., [10,[25][26][27][28][29][30][31][32][33][34][35][36][37]). Unlike all previous literature, however, we provide a general taxonomy of ML-specific security in terms of each vulnerable asset.…”

Section: Related Workmentioning

confidence: 99%

Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomy

Kawamoto¹,

Miyake²,

Konishi³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this article, we propose the Artificial Intelligence Security Taxonomy to systematize the knowledge of threats, vulnerabilities, and security controls of machine-learning-based (ML-based) systems. We first classify the damage caused by attacks against ML-based systems, define ML-specific security, and discuss its characteristics. Next, we enumerate all relevant assets and stakeholders and provide a general taxonomy for ML-specific threats. Then, we collect a wide range of security controls against ML-specific threats through an extensive review of recent literature. Finally, we classify the vulnerabilities and controls of an ML-based system in terms of each vulnerable asset in the system's entire lifecycle.

show abstract

“…AI-led attacks will be able to maintain a long-term stealth presence in the target environment and compromise more devices than ever before (Zhang et al, 2018). Offensive AI will also be able to carry out targeted attacks with unprecedented speed and scale, without requiring the research and prior knowledge that human attackers currently need (Mirsky et al, 2021). Therefore, cyber security researchers face many challenges in developing more intelligent, environment-aware autonomous systems that can defend against these evolving cyber attack capabilities.…”

Section: Introductionmentioning

confidence: 99%

Towards Autonomous Cyber Defense: Predictions from a cognitive model

Prebot

et al. 2022

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

We propose that cognitive models will help advance autonomous cyber defense. Congitive models, in contrast to many other sophisticated approaches, such as machine learning models, have the ability to represent human actions, account for human cognitive constraints, and make more accurate predictions of the decisions a human would make. The success of cyber defense largely depends on the ability to predict the attacker’s actions, and expert cyber defenders acquire such an ability through experience. We propose a cognitive model of a cyber defender and demonstrate the model’s predictions in a simple but realistic scenario against two types of attack strategies and under various conditions of noise and feedback frequency regarding the attacker’s actions. The results of the simulations illustrate the expected impact on defense losses when attackers are more knowledgeable,fast, and directed in their attacks compared to when an attacker meanders around; results show how losses increase in the presence of normal activity and how a defender can benefit from receiving feedback less often to reduce losses. We discuss the implications of these results for the future of autonomous cyber defense.

show abstract

The Threat of Offensive AI to Organizations

Cited by 22 publications

References 63 publications

Warning: Humans Cannot Reliably Detect Speech Deepfakes

Warning: Humans Cannot Reliably Detect Speech Deepfakes

Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomy

Towards Autonomous Cyber Defense: Predictions from a cognitive model

Contact Info

Product

Resources

About