Securing.AI – AI Security, Safety and Privacy

January 1, 2024

Marin’s Statement on AI Risk

August 23, 2024

Addressing the Full Stack of AI Concerns: Responsible AI, Trustworthy AI, Secure AI and Safe AI Explained

September 5, 2026

AI Deployment Security: Build the Boundary Outside the Model

October 17, 2024

Closing the Gap Between AI Principles and AI Reality

April 7, 2024

The Dual Risks of AI Autonomous Robots: Uncontrollable AI Meets Cyber-Kinetic Risks

September 20, 2023

Why We Need a Chief AI Security Officer (CAISO)

Our Latest Articles

AI Geopolitics

Marin IvezicSeptember 6, 2026

Reading Superpowers and AGI: Bombing Data Centres Is an Old Idea, and It Is Not Disarmament

A report on AGI and US-China competition spent last week being reported as a proposal to bomb Chinese data centres.…
Read More »
AI Privacy

Marin IvezicSeptember 6, 2026

Federated Learning Privacy Depends on What the Server Is Allowed to Send

Federated learning keeps raw data on the device, and the security question that decides your actual risk is not whether…
Read More »
AI Security

Marin IvezicSeptember 6, 2026

AI Model Security: How It Differs from Traditional Cybersecurity, and Where It Doesn’t

For most organisations, AI security is still conventional security applied to an unfamiliar stack. Where AI does add new failure…
Read More »
AI Security

Marin IvezicSeptember 6, 2026

Adversarial Training: What It Buys, What It Costs, and Where It Stops Working

Adversarial training is the one defence against adversarial examples that keeps surviving adaptive attack. It also costs an order of…
Read More »
AI Security

Marin IvezicSeptember 6, 2026

Robust Optimization Is the Only Defence That Held, and Only Inside Its Own Threat Model

Adversarial training as robust optimization is the only defence in fifteen years of adversarial machine learning that has survived attacks…
Read More »
AI Security

Marin IvezicSeptember 5, 2026

AI Deployment Security: Build the Boundary Outside the Model

A model in production will misread a document, accept a malicious premise or propose the wrong action. Securing the deployment…
Read More »
AI Security

Marin IvezicSeptember 5, 2026

White-Box vs. Black-Box Attacks: What Access Actually Buys

The attacker's access class used to predict how strong an attack would be. For LLM systems it no longer does…
Read More »
Agentic AI Security

Marin IvezicSeptember 5, 2026

The AI Act Now Recognises Agents. Its Security Rules Still Miss Them.

The Commission's AI Act Service Desk says agents are covered by the existing definitions and calls its own considerations preliminary.…
Read More »
AI Governance and Policy

Marin IvezicSeptember 5, 2026

One AI Incident, Four Reporting Regimes, and the Carve-Outs That Decide Which Apply

Cyber Resilience Act reporting starts 11 September 2026, joining three other European regimes. The AI Act already limits its own…
Read More »

Previous Next

Marin Ivezic

In the early 2000s, running emerging-technology risk labs at CyberAgency, a defence client asked my team to break the AI systems they planned to put into weapons. We did. That is where my work on AI security started, two decades before the current wave of attention. I kept at it through risk labs at IBM, Accenture, PwC and KPMG. In 2016 I co-wrote a book on AI and leadership. My commercial work today is quantum, at Applied Quantum, which is why this site sells nothing.

Luka Ivezic

Luka Ivezic co-wrote The Future of Leadership in the Age of AI with Marin in 2016, and co-authored much of the early writing on this site. He is Practice Lead, Regulations & Emerging Technologies at the Information Security Forum, where he covers EU regulation and the security of AI, OT and IoT. He was previously a cybersecurity consultant at PwC and Deloitte. He holds a Master’s in International Conflict Studies from King’s College London, where his research examined the security implications of AI.

Most Viewed Articles This Week

September 6, 2026

AI Security Articles

AI Security

Marin IvezicSeptember 6, 2026

AI Model Security: How It Differs from Traditional Cybersecurity, and Where It Doesn’t

For most organisations, AI security is still conventional security applied to an unfamiliar stack. Where AI does add new failure modes, hardening the model will not reliably remove them. What changes, what doesn't, and what to do on Monday.
Read More »
AI Security

Marin IvezicSeptember 6, 2026

Adversarial Training: What It Buys, What It Costs, and Where It Stops Working

Adversarial training is the one defence against adversarial examples that keeps surviving adaptive attack. It also costs an order of magnitude in compute, several points of clean accuracy, and stops working once you cannot write the threat model down.
Read More »
AI Security

Marin IvezicSeptember 6, 2026

Robust Optimization Is the Only Defence That Held, and Only Inside Its Own Threat Model

Adversarial training as robust optimization is the only defence in fifteen years of adversarial machine learning that has survived attacks built to break it. What it costs, where it stops, and what to ask a vendor.
Read More »
AI Security

Marin IvezicSeptember 5, 2026

AI Deployment Security: Build the Boundary Outside the Model

A model in production will misread a document, accept a malicious premise or propose the wrong action. Securing the deployment means building the boundary outside the model, so a fooled model cannot exceed the consequences the organisation authorised.
Read More »
AI Security

Marin IvezicSeptember 5, 2026

White-Box vs. Black-Box Attacks: What Access Actually Buys

The attacker's access class used to predict how strong an attack would be. For LLM systems it no longer does on its own, and the two labels have started hiding the question that matters: what did the attacker actually…
Read More »
AI Security

Marin IvezicSeptember 5, 2026

Article 15 Requires Robustness Nobody Can Measure

Article 15(5) runs to three sentences and most summaries quote only the first. The other two set a proportionality standard nobody can measure, because no benchmark, no harmonised standard and no threat-model-independent robustness metric exists.
Read More »

Previous Next

AI Safety Articles

Marin IvezicAugust 15, 2026

Three Capability Scores for One Model, and METR Disowned All Three

METR produced three capability estimates for one model, ranging from 11 hours to over 270, and said none of them was a robust measurement. The UK AI Security Institute found every frontier model it tested attempted to cheat.
Read More »
AI Safety and Alignment

Marin IvezicJanuary 1, 2024

Marin’s Statement on AI Risk

The rapid development of AI brings both extraordinary potential and unprecedented risks. AI systems are increasingly demonstrating emergent behaviors, and in some cases, are even capable of self-improvement. This advancement, while remarkable, raises critical questions about our ability to control and understand these systems fully.
Read More »
AI Safety and Alignment

Marin Ivezic and Luka IvezicJune 29, 2023

The AI Alignment Problem

The AI alignment problem sits at the core of all future predictions of AI’s safety. It describes the complex challenge of ensuring AI systems act in ways that are beneficial and not harmful to humans, aligning AI goals and decision-making processes with those of humans, no matter how sophisticated or powerful the AI system becomes. Our trust in the future…
Read More »
AI Safety and Alignment

Marin Ivezic and Luka IvezicNovember 24, 2022

“Magical” Emergent Behaviours in AI: A Security Perspective

Emergent behaviours in AI have left both researchers and practitioners scratching their heads. These are the unexpected quirks and functionalities that pop up in complex AI systems, not because they were explicitly trained to exhibit them, but due to the intricate interplay of the system's complexity, the sheer volume of data it sifts through, and its interactions with other systems…
Read More »
AI Safety and Alignment

Marin Ivezic and Luka IvezicDecember 26, 2021

Explainable AI Frameworks in 2026: What Still Ships

This page recommended eight explainable AI frameworks in 2021. Only SHAP is still releasing. A census of what stopped, what replaced it, and where the interpretability effort went instead.
Read More »
AI Safety and Alignment

Marin IvezicMay 4, 2019

Risks of AI – Meeting the Ghost in the Machine

Because it demands so much manpower, cybersecurity has already benefited from AI and automation to improve threat prevention, detection and response. Preventing spam and identifying malware are already common examples. However, AI is also being used – and will be used more and more – by cybercriminals to circumvent cyberdefenses and bypass security algorithms. AI-driven cyberattacks have the potential to…
Read More »

AI Privacy Articles

AI Privacy

Marin IvezicSeptember 6, 2026

Federated Learning Privacy Depends on What the Server Is Allowed to Send

Federated learning keeps raw data on the device, and the security question that decides your actual risk is not whether gradients leak but whether the party running the aggregation server is honest, and whether your clients could tell.
Read More »
AI Privacy

Marin IvezicAugust 27, 2026

Secure Multi-Party Computation Hides the Inputs, Not the Answer

Secure multi-party computation protects the inputs to a computation and reveals the output exactly as computed. In machine learning the output is a model or a prediction, and both leak. What MPC covers, what its benchmarks assume, and what to ask.
Read More »
AI Privacy

Marin Ivezic and Luka IvezicJuly 21, 2023

Homomorphic Encryption for ML: What the Overhead Buys

Homomorphic encryption lets an untrusted server compute on data it cannot read. The overhead is severe enough that the set of machine learning workloads where that trade is correct is small, specific and worth naming precisely.
Read More »
AI Privacy

Marin Ivezic and Luka IvezicJune 2, 2022

Differential Privacy Protects the Training Set, Not the System

What epsilon actually guarantees, why deployed values sit near 10, and what differential privacy leaves uncovered in a 2026 AI system.
Read More »
AI Privacy

Marin Ivezic and Luka IvezicFebruary 11, 2021

What Model Inversion Attacks Actually Recover

Model inversion recovers class representatives more often than individuals, its dominant evaluation framework counts adversarial examples as successful reconstructions, and embedding inversion has become a separate privacy problem in enterprise retrieval systems.
Read More »
AI Privacy

Marin Ivezic and Luka IvezicFebruary 8, 2018

The Future of Privacy in our Smart Living – Part 2

In a world where the population is increasing and resources are finite, we need to find smarter ways of living together. Smart technologies hold the key to making this happen but we need to proceed with caution and build a layer of respectful trust and privacy in our smart places.
Read More »

Previous Next

AI Disinformation Articles

AI Disinformation

Marin IvezicSeptember 5, 2026

The AI Act’s Transparency Code Relies on Watermarks That Break

Article 50 requires marking that is effective and robust as far as technically feasible, and prescribes no technique. The Code selects watermarking and provenance metadata. Published attacks remove both and forge the second.
Read More »
AI Disinformation

Marin Ivezic and Luka IvezicDecember 6, 2022

Introduction to AI-Enabled Disinformation

In recent years, the rise of artificial intelligence (AI) has revolutionized many sectors, bringing about significant advancements in various fields. However, one area where AI has presented a dual-edged sword is in information operations, specifically in the propagation of disinformation. The advent of generative AI, particularly with sophisticated models capable of creating highly realistic text, images, audio, and video, has…
Read More »
AI Disinformation

Marin Ivezic and Luka IvezicAugust 7, 2020

Targeted Disinformation

Targeted disinformation poses a significant threat to societal trust, democratic processes, and individual well-being. The use of AI in these disinformation campaigns enhances their precision, persuasiveness, and impact, making them more dangerous than ever before. By understanding the mechanisms of targeted disinformation and implementing comprehensive strategies to combat it, society can better protect itself against these sophisticated threats.
Read More »
AI Disinformation

Marin Ivezic and Luka IvezicMarch 15, 2019

AI-Exacerbated Disinformation and Threats to Democracy

Recent events have confirmed that the cyber realm can be used to disrupt democracies as surely as it can destabilize dictatorships. Weaponization of information and malicious dissemination through social media pushes citizens into polarized echo chambers and pull at the social fabric of a country. Present technologies enhanced by current and upcoming Artificial Intelligence (AI) capabilities, could greatly exacerbate disinformation…
Read More »

AI (Other) Articles

AI Perspectives

Marin Ivezic and Luka IvezicMay 23, 2023

A (Very) Brief History of AI

As early as the mid-19th century, Charles Babbage and Ada Lovelace created the Analytical Engine, a mechanical general-purpose computer. Lovelace is often credited with the idea of a machine that could manipulate symbols in accordance with rules and that it might act upon other than just numbers, touching upon concepts central to AI.
Read More »
AI Perspectives

Marin IvezicDecember 14, 2018

Introducing Quantum Artificial Intelligence (QAI): The Future Intersection of Quantum Computing and AI

Table of ContentsIntroductionExponential Growth in AI Computing RequirementsIntroduction to Quantum Artificial Intelligence (QAI)Why Quantum Computers Are Well-Suited for Manipulating Vectors and Matrices Required by AIRecent Key Quantum Artificial Intelligence (QAI) Research PapersQuantum Machine Learning AlgorithmsApplications of Quantum AIChallenges and Future DirectionsConclusion Introduction (This article was originally published in 2018. Updated in 2022 after the release of ChatGPT) While I like…
Read More »
AI Perspectives

Marin IvezicFebruary 6, 2018

AI Is Neither the End of Civilization nor the Beginning of Nirvana

Where AI, robots, IoT and the so-called Fourth Industrial Revolution are taking us, and how we should prepare for it are some of the hottest topics being discussed today. Perhaps the most striking thing about these discussions is how different people’s conclusions are. Some picture a utopia where machines do all work, where all people receive a universal basic income…
Read More »
AI Perspectives

Marin IvezicFebruary 2, 2018

AI Uses Today – Far More Than You Might Think

Ask people on the street how much AI uses today affect their lives, and most would probably answer that it doesn’t affect them right now. Some might say that it’s pure science fiction. Others might say that it may affect our future but isn’t used in our world today. Some might correctly identify a few ways it’s used in modern…
Read More »
AI Perspectives

Marin IvezicMarch 3, 2017

Seventy Years On, AI Still Evaluates Itself the Way Dartmouth Did

AI's founding document was a grant application whose central claim went far beyond anything it could show. Notes from the summer of 1956 record two failure questions a security practitioner would recognise, and the field kept neither.
Read More »