NIST Fortifies Chatbots and Self-Driving Cars Against Digital Threats

In a landmark move, the US National Institute of Standards and Technology has taken a new step in developing strategies to fight against cyber-threats that target AI-powered chatbots and self-driving cars.
The Institute released a new paper on January 4, 2024, in which it established a standardized approach to characterizing and defending against cyber-attacks on AI. The paper, called Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations, was written in collaboration with academia and industry.
It documents the different types of adversarial machine learning attacks and some mitigation techniques.
What NIST calls 'predictive AI' refers to a broad understanding of AI and machine learning systems that predict behaviors and phenomena.
An example of such systems can be found in computer vision devices or self-driving cars.
'Generative AI,' in NIST taxonomy, is a sub-category within 'predictive AI,' which includes generative adversarial networks, generative pre-trained transformers and diffusion models.
Evasion attacks, in which the adversary's goal is to generate adversarial examples, which are defined as testing samples whose classification can be changed at a deployment time to an arbitrary class of the attacker's choice with only minimal perturbation.
Poisoning attacks, referring to adversarial attacks conducted during the training stage of the AI algorithm.
Privacy attacks, attempts to learn sensitive information about the AI or the data it was trained on in order to misuse it.
AML attacks targeting 'generative AI' systems fall under a fourth category, which NIST calls abuse attacks.
They involve the insertion of incorrect information into a source, such as a webpage or online document, that an AI then absorbs.
Unlike poisoning attacks, abuse attacks attempt to give the AI incorrect pieces of information from a legitimate but compromised source to repurpose the AI system's intended use.
The authors provided some mitigation techniques and approaches for each of these categories and sub-categories of attacks.
Apostol Vassilev, a computer scientist at NIST and one of the co-authors, admitted that they are still largely insufficient.
NIST's Effort to Support the Development of Trustworthy AI. The publication of this paper comes three months after the release of Joe Biden's Executive Order on Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence.
The EO tasked NIST to support the development of trustworthy AI. The taxonomy introduced in the NIST paper will also serve as a basis to put into practice NIST's AI Risk Management Framework, which was first released in January 2023.
In November 2023 at the UK's AI Safety Summit, US Vice-President Kamala Harris announced the creation of a new entity within NIST, the US AI Safety Institute.
The Institute's mission is to facilitate the development of standards for the safety, security, and testing of AI models, develop standards for authenticating AI-generated content, and provide testing environments for researchers to evaluate emerging AI risks and address known impacts.
The UK also inaugurated its own AI Safety Institute during the summit.


This Cyber News was published on www.infosecurity-magazine.com. Publication date: Fri, 05 Jan 2024 12:30:13 +0000


Cyber News related to NIST Fortifies Chatbots and Self-Driving Cars Against Digital Threats

NIST Fortifies Chatbots and Self-Driving Cars Against Digital Threats - In a landmark move, the US National Institute of Standards and Technology has taken a new step in developing strategies to fight against cyber-threats that target AI-powered chatbots and self-driving cars. The Institute released a new paper on ...
10 months ago Infosecurity-magazine.com
9 Best DDoS Protection Service Providers for 2024 - eSecurity Planet content and product recommendations are editorially independent. We may make money when you click on links to our partners. Learn More. One of the most powerful defenses an organization can employ against distributed ...
11 months ago Esecurityplanet.com
Teaching Digital Ethics: Navigating the Digital Age - In today's digital age, where technology permeates every aspect of our lives, the need for ethical behavior in the digital realm has become increasingly crucial. This article explores the significance of digital ethics education in our society and ...
10 months ago Securityzap.com
Chatbots and Human Conversation - If you wanted results, you needed to learn the computer's language. Large language models-the technology undergirding modern chatbots-allow users to interact with computers through natural conversation, an innovation that introduces some baggage from ...
9 months ago Schneier.com
Building a Culture of Digital Responsibility in Schools - In today's technologically-driven world, schools have a critical role in cultivating a culture of digital responsibility among students. Promoting digital responsibility involves educating students about the potential risks and consequences ...
10 months ago Securityzap.com
Digital Citizenship Lessons for Students - This article aims to emphasize the significance of digital citizenship lessons for students, focusing on three key aspects: the definition and scope of digital citizenship, online etiquette, and safe online behavior. By equipping students with ...
10 months ago Securityzap.com
Strengthening Cybersecurity: The Role of Digital Certificates and PKI in Authentication - Data protection remains integral in our wide digital world. This has been possible because of the increasing awareness amidst enterprises, small and large, across industries on the paramount need for the protection of sensitive data, securing digital ...
9 months ago Feeds.dzone.com
CMMC v2.0 vs NIST 800-171: Understanding the Differences - The NIST SP 800-171 lays out the requirements for any non-federal agency that handles controlled unclassified information, or other sensitive federal information. DFARS does not address the CMMC at all but a new clause is currently being drafted for ...
10 months ago Securityboulevard.com
The Evolution of Cyber Threats: Past, Present, and Future - Cyber threats have evolved significantly over time, posing increasing risks to individuals, organizations, and governments in our interconnected world. Let's explore the past, present, and future of cyber threats to better understand how to protect ...
9 months ago Securityzap.com
Accelerating Safe and Secure AI Adoption with ATO for AI: stackArmor Comments on OMB AI Memo - We appreciate the opportunity to comment on the proposed Memo on Agency Use of Artificial Intelligence. Ensuring agencies have access to adequate IT infrastructure,. We base our remarks on our experience helping US Federal agencies transform their ...
10 months ago Securityboulevard.com
Chatbots: Transforming Tech, Creating Jobs, and Making Waves - Not too long ago, chatbots were seen as fun additions to customer service. They have evolved significantly with advancements in AI, machine learning, and natural language processing. A recent report suggests that the chatbot market is set for ...
9 months ago Cysecurity.news
How Smart Car is Probably Tracking You? - According to ExpressVPN, there's a concerning number of car manufacturers that collect data on their drivers, and an impressive 84% of them then share or sell this data. Connected to the car's Wi-Fi network, modern smart cars' infotainment systems ...
10 months ago Cybersecuritynews.com
Driving into Tomorrow: The AI powered Car Takeover - In the next decade, a tech-driven revolution is set to transform our roads as 95% of vehicles become AI-powered connected cars. These smart vehicles, while promising enhanced safety and convenience, come with a catch-each generating a whopping 25 ...
9 months ago Cysecurity.news
AI Will Be Powerful, But No Panacea - Anyone following the deployment of self-driving cars knows the technology is proving far from foolproof. The issues, largely, are in the thousands of little variations in traffic patterns that speckle our driving lives, to which machines often fail ...
10 months ago Cybersecurity-insiders.com
What is the NIST Cybersecurity Framework? Definition from SearchSecurity - The NIST Cybersecurity Framework provides guidance on how to manage and reduce IT infrastructure security risk. NIST created the CSF to help private sector organizations in the United States develop a roadmap for critical infrastructure ...
9 months ago Techtarget.com
Protecting Your Digital Realm: Understanding Cybersecurity Threats and Defenses - Understanding the different types of cyber attacks and implementing robust security measures is crucial in safeguarding sensitive data and systems from malicious intent. In the dynamic landscape of cyberspace, threats to digital security continue to ...
9 months ago Feeds.dzone.com
What a Digital ID Means to How Australians Interact With Businesses Online - Australia is about to get a national online ID system - the Digital ID - which promises to improve the security and privacy of data online. In just a few months, Australians will have access to a new form of ID, which aims to make identification ...
10 months ago Techrepublic.com
Does Your App Accept Digital Wallets? - Digital wallets are electronic systems that securely store payment information digitally. Digital wallets are designed for convenience and often include security features to protect your financial data. How Digital Wallets Function Digital wallets ...
10 months ago Feeds.dzone.com
A Deep Dive Into How Digital Pound Can Menace Financial Stability - The UK's expedition into releasing a digital pound has triggered a strong debate among policymakers and finance experts. The House of Commons Treasury Committee has shown concerns, cautioning that bringing a central bank digital currency in the UK ...
11 months ago Cysecurity.news
Tensorflow Supply Chain Compromise via Self-Hosted Runner Attack - Let's say TensorFlow wants to run a set of tests when a GitHub user submits a pull request. TensorFlow can define these tests in a yaml workflow file, used by GitHub Actions, and configure the workflow to run on the `pull request` trigger. One type ...
9 months ago Securityboulevard.com
Teaching Digital Literacy and Online Safety - It is crucial for educators to prioritize teaching online safety to ensure that students are equipped with the necessary skills to protect themselves online. This article aims to explore the importance of teaching digital literacy and online safety, ...
10 months ago Securityzap.com
How the FTC Can Make the Internet Safe for Chatbots - No points for guessing the subject of the first question the Wall Street Journal asked FTC Chair Lina Khan: of course it was about AI. Between the hype, the lawmaking, the saber-rattling, the trillion-dollar market caps, and the predictions of ...
4 months ago Eff.org
GM Sues San Francisco Over $108m Tax Bill - Parent company of robotaxi firm Cruise, General Motors, files lawsuit against San Francisco over $108m tax bill. General Motors has filed a lawsuit against the city of San Francisco, in a tax dispute centred around its Cruise self-driving division. ...
10 months ago Silicon.co.uk
Cybersecurity Trends: Shaping the Future Landscape - Embark on a journey through the ever-evolving landscape of cybersecurity, where hidden threats and silent breaches shape the digital realm. AI is transforming the cybersecurity landscape by enhancing threat detection and mitigation, ushering in a ...
7 months ago Securityzap.com
How AI can be hacked with prompt injection: NIST report - As AI proliferates, so does the discovery and exploitation of AI cybersecurity vulnerabilities. Prompt injection is one such vulnerability that specifically attacks generative AI. In Adversarial Machine Learning: A Taxonomy and Terminology of Attacks ...
7 months ago Securityintelligence.com

Latest Cyber News


Cyber Trends (last 7 days)


Trending Cyber News (last 7 days)