Adversa releases Secure and Trusted AI report with exclusive retrospective, trends, predictions

Adversa, an Israeli leader in Secure and Trusted AI research and advisory, has published comprehensive research on the security and trustworthiness of AI systems worldwide during the last decade.

In the extensive report, “The road to secure and Trusted AI”, Adversa reveals the most critical real-world security threats facing AI and effective countermeasures to protect these systems. The research considers the impact of ongoing regulations concerning AI security in the EU and USA.

Oliver Rochford, Adversa Advisor and former Gartner Analyst, says:

Building trust in the security and safety of machine learning is crucial. We are asking people to put their faith in what is essentially a black box, and for the AI revolution to succeed, we must build trust. And we can’t bolt security on this time. We won’t have many chances at getting it right. The risks are too high – but so are the benefits.

The research provides a comprehensive overview of the state of AI security over the past ten years and includes many insightful statistics and infographics.

Eugene Neelou, Adversa’s CTO states:

To raise security awareness in the field of Trusted AI, we started more than a year ago a project to analyze the past decade of academic, industry, and governmental progress. The eye-opening results reveal an exponential growth of interest in testing AI systems for security and Bias and the absence of adequate defenses. Organizations should keep up with the latest threats, implement AI security awareness initiatives, and protect their AI development life cycle especially now. 

The report,  “The Road to Secure and Trusted AI”, is written for anyone responsible for AI risk and security and compiles experts’ opinion and predictions from across the field. Some highlight from the findings include:

• Real-world AI incidents are growing in the automotive, biometrics, robotics, and internet industries. Being early AI adopters, the most scrutinized industries are the internet (23%), cybersecurity (17%),  biometrics (16%), and autonomous (13%).
• The recent exponential growth of AI has motivated governments, academia, and industry to publish more research on AI Security for the past two years than for the previous two decades totaling over 3500 papers.
• The most targeted AI area is computer vision (65%) followed by analytics and language. 
• The USA-China-EU standoff is expected to continue in the Trusted AI race with the USA responsible for 47% of all research papers, but China (13%) is growing at a higher rate and can surpass in the following years.
• Top 3 countries by research papers per capita are Switzerland, Singapore and Israel.
• The AI industry is woefully unprepared for real-world attacks against AI systems, every ML model of top 60 commonly used in industry are prone to at least one vulnerability.

Alex Polyakov, Founder and CEO of Adversa, comments:

Unfortunately, our investigation shows that the AI industry is alarmingly unready for the wave of coming real-world attacks against AI systems. Public perception of how trustworthy AI is will be a core criterion determining whether societies and businesses will adopt AI for good or face another AI winter. We have to build trust in AI, based on the early adoption of suitable standards  and testing approaches, like this being developed by MITRE. And we have to do this together, as a community. That’s our mission at Adversa, to help build that groundwork early, and our new research lays out the problem statement for that. 

Other discoveries of the report:

• The most threatening attacks research and their effect on businesses and economies;
• Countries dominating in terms of the number of research papers and industry initiatives; 
• Expert viewpoints on the AI security and predictions for the industry’s further growth;
• Deep scientific research and annotation of 2000+ academic papers, which were published from 2010 till nowadays; 
• Real incidents and governmental initiatives happened during the last decade.

Adversa is spearheading the effort for more secure artificial intelligence and invites enthusiasts, researchers, and industry partners to join the team on the road to secure and trusted AI. After this initial publication, we are planning to continue raising awareness on AI security on a monthly basis. 

Subscribe to newsletters to be the first to know the hottest news and latest analytics.

About Adversa

Adversa is the leading Israeli company developing applied security measures for Artificial Intelligence (AI). Our mission is to build trust in AI by protecting them from cyber threats, privacy issues, and safety incidents. With the team of multi-disciplinary experts in mathematics, data science, cybersecurity, and neuroscience, Adversa is uniquely able to provide holistic, end-to-end support for the entire AI Security Lifecycle, from security awareness and risk assessment to solution design and maintaining full AI security programs.