Securing AI Systems: A Guide to Known Attacks and Impacts
Not on the map. Why?
Abstract (arXiv)
Embedded into information systems, artificial intelligence (AI) faces security threats that exploit AI-specific vulnerabilities. This paper provides an accessible overview of adversarial attacks unique to predictive and generative AI systems. We identify eleven major attack types and explicitly link attack techniques to their impacts -- including information leakage, system compromise, and resource exhaustion -- mapped to the confidentiality, integrity, and availability (CIA) security triad. We aim to equip researchers, developers, security practitioners, and policymakers, even those without specialized AI security expertise, with foundational knowledge to recognize AI-specific risks and implement effective defenses, thereby enhancing the overall security posture of AI systems.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 56 of its 110 references that are in the map. First posted on arXiv 29 Jun 2025.
Builds on
56 of 110 references.
References · 56
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2013Intriguing properties of neural networkscited by 5,155
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
- 2020Extracting Training Data from Large Language Modelscited by 2,189
- 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
- 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
- 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,420
- 2022Red Teaming Language Models with Language Modelscited by 1,026
- 2016Practical Black-Box Attacks against Machine Learningcited by 903
- 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
- 2023Extracting Training Data from Diffusion Modelscited by 732
- 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
38 more
- 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 672
- 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
- 2016Stealing Machine Learning Models via Prediction APIscited by 619
- 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
- 2024WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMscited by 496
- 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
- 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 443
- 2024Improving Alignment and Robustness with Circuit Breakerscited by 322
- 2023Are aligned neural networks adversarially aligned?cited by 315
- 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 292
- 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 285
- 2024Defending Against Indirect Prompt Injection Attacks With Spotlightingcited by 267
- 2021Gradient-based Adversarial Attacks against Text Transformerscited by 234
- 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 225
- 2019Explanations can be manipulated and geometry is to blamecited by 216
- 2018Adversarial Robustness Toolbox v1.0.0cited by 215
- 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 194
- 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 186
- 2024Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMscited by 173
- 2017Machine Learning Models that Remember Too Muchcited by 169
- 2018PRADA: Protecting against DNN Model Stealing Attackscited by 165
- 2022Reconstructing Training Data with Informed Adversariescited by 148
- 2022Reconstructing Training Data from Trained Neural Networkscited by 133
- 2013Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifierscited by 130
- 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 130
- 2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 124
- 2018Stealing Hyperparameters in Machine Learningcited by 118
- 2020Sponge Examples: Energy-Latency Attacks on Neural Networkscited by 111
- 2018Understanding Membership Inferences on Well-Generalized Learning Modelscited by 90
- 2023Effective Prompt Extraction from Language Modelscited by 85
- 2019Overlearning Reveals Sensitive Attributescited by 76
- 2018Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Datacited by 70
- 2019IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundarycited by 70
- 2020ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learningcited by 70
- 2023Prompt Stealing Attacks Against Text-to-Image Generation Modelscited by 51
- 2021Poisoning the Unlabeled Dataset of Semi-Supervised Learningcited by 44
- 2021DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memoriescited by 42
- 2023The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Riskscited by 36
50 most cited of 56 All 56 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.