NIST: Better Defenses are Needed for AI Systems

The accelerating development and expanding deployment of AI systems is creating significant security and privacy risks that aren't being mitigated by modern solutions, according to a research paper from the U.S. National Institute of Standards and Technology.
The cybersecurity community needs to develop better defenses, Vassilev said.
The report outlines that predictive and generative AI systems include data, machine learning models, and processes for training, testing, and deploying the models and necessary infrastructure.
Generative AI system also can be linked to corporate documents and databases.
These kinds of attacks already are happening and their sophistication and potential impact are increasing.
The report four types of attacks that can occur on AI systems, including evasion attacks, where a bad actor will try to alter an input to change how a system responds to it, such as adding markings that make autonomous vehicles misinterpret road signs.
Poisoning attacks involved adding corrupted data to a training dataset and privacy attacks hit when threat actors try to access sensitive information about the AI or the data an AI system was trained on in hopes of misusing it.
Abuse attacks involve inserting incorrect information into a source, like a legitimate webpage or online document, that an AI system pulls in.
In the report, the researchers talk about the size of the large-language models used to create generative AI and the large datasets being used to train them.
A challenge is that the datasets are too large for individuals to monitor and filter properly, so there are no foolproof methods for protecting AI from misdirection, they wrote.
It's important that developers and organizations that want to deploy and use AI technologies are aware of the limitations, according to Vassilev.
The paper is part of the White House's whole-of-government approach to dealing with the growing threat presented by the rapid innovation around AI. NIST last year unveiled its AI Risk Management Framework and is seeking comments through February 2 on its efforts to create trustworthy ways of developing and using AI. Other agencies also are taking on the challenge of securing AI development.
The Cybersecurity and Infrastructure Security Agency in August 2023 advised developers that AI applications - like all software - need to have security designed into them.
The same month, the U.S. Defense Advanced Research Projects Agency unveiled the AI Cyber Challenge to urge cybersecurity and AI specialists to create ways to automatically detect and fix software flaws and protect critical infrastructure.
High-profile companies like Google, Microsoft, OpenAI, and Meta are working with the White House to address risks posed by AI, and Google, Microsoft, OpenAI, and Anthropic in July 2023 announced the Frontier Model Forum, an industry group developing ways to ensure the safe development of foundation AI models.
In November, the Federal Trade Commission and Federal Communications Commission announced separate efforts to protect consumers against scammers using AI-enabled voice technologies in fraud and other schemes, with the FTC this month asking for submissions for ways to address the malicious use of voice-cloning technologies.
The same agency also is hosting a virtual summit January 25 to talk about the emerging AI market and its potential impacts.


This Cyber News was published on securityboulevard.com. Publication date: Mon, 08 Jan 2024 17:43:49 +0000


Cyber News related to NIST: Better Defenses are Needed for AI Systems

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
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
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
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
Preparing for Q-Day as NIST nears approval of PQC standards - Q-Day-the day when a cryptographically relevant quantum computer can break most forms of modern encryption-is fast approaching, leaving the complex systems our societies rely on vulnerable to a new wave of cyberattacks. While estimates just a few ...
4 months ago Helpnetsecurity.com
Preparing for Q-Day as NIST nears approval of PQC standards - Q-Day-the day when a cryptographically relevant quantum computer can break most forms of modern encryption-is fast approaching, leaving the complex systems our societies rely on vulnerable to a new wave of cyberattacks. While estimates just a few ...
4 months ago Helpnetsecurity.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
NIST: No Silver Bullet Against Adversarial Machine Learning Attacks - NIST has published a report on adversarial machine learning attacks and mitigations, and cautioned that there is no silver bullet for these types of threats. Adversarial machine learning, or AML, involves extracting information about the ...
9 months ago Securityweek.com
The Embedded Systems and The Internet of Things - The Internet of Things is a quite new concept dealing with the devices being connected to each other and communicating through the web environment. This concept is gaining its popularity amongst the embedded systems that exist - let's say - 10 or ...
10 months ago Cyberdefensemagazine.com
IT and OT cybersecurity: A holistic approach - In comparison, OT refers to the specialized systems that control physical processes and industrial operations. OT Technologies include industrial control systems, SCADA systems and programmable logic controllers that directly control physical ...
10 months ago Securityintelligence.com
NIST: Better Defenses are Needed for AI Systems - The accelerating development and expanding deployment of AI systems is creating significant security and privacy risks that aren't being mitigated by modern solutions, according to a research paper from the U.S. National Institute of Standards and ...
9 months ago Securityboulevard.com
Creating a New Market for Post-Quantum Cryptography - A day in the busy life of any systems integrator includes many actions that revolve around the lifeblood of its business - its customers. Systems integrators help solve evolving customer business challenges, which in turn adds partner value. It's a ...
10 months ago Securityboulevard.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
Cybersecurity In Critical Infrastructure: Protecting Power Grids and Smart Grids - Cyber Defense Magazine - Network Intrusion: Network communication systems of power and smart grids can be intruded through weak security configurations like default password, unsecured remote access, or unpatched systems and other vulnerabilities to gain control into the ...
1 month ago Cyberdefensemagazine.com
The US National Institute of Standards and Technology Announces the Successful Encryption Algorithm for Securing Internet of Things Data - The National Institute of Standards and Technology (NIST) recently announced that ASCON was the winning bid for its Lightweight Cryptography Program. This program was designed to find the best algorithm to protect small Internet of Things (IoT) ...
1 year ago Bleepingcomputer.com
How the New NIST 2.0 Guidelines Help Detect SaaS Threats - The SaaS ecosystem has exploded in the six years since the National Institute of Standards and Technology's cybersecurity framework 1.1 was released. Back in 2016-2017, when version 1.1 was initially drafted, SaaS held a small but significant place ...
7 months ago Bleepingcomputer.com
NIST Confusion Continues as Cyber Pros Complain CVE Uploads Stopped - A recent rise in software vulnerability exploits has come as the US National Vulnerability Database, the world's most comprehensive vulnerability database, experiences its most significant crisis in history. After experiencing a vulnerability ...
5 months ago Infosecurity-magazine.com
Vanta announces new offerings to meet the needs of modern GRC and security leaders - Vanta announced a number of new and upcoming product launches enabling customers to accelerate innovation and strengthen security. The new offerings include advanced Reporting to help security professionals measure the success of their security ...
11 months ago Helpnetsecurity.com
NIST NVD Disruption Sees CVE Enrichment on Hold - Since February 12, 2024, NIST has almost completely stopped enriching software vulnerabilities listed in its National Vulnerability Database, the world's most widely used software vulnerability database. Tom Pace, CEO of firmware security provider ...
7 months ago Infosecurity-magazine.com
Embedded Linux IoT Security: Defending Against Cyber Threats - Embedded Linux IoT systems are now essential parts of many different kinds of products, from industrial machinery and smart appliances to medical equipment and automobile systems. As Embedded Linux is being used widely, it has attracted the attention ...
9 months ago Securityboulevard.com
Examining if NISTs Cybersecurity Framework 20 Could Lead to Global Standards - It has been almost seven years since the 1.1 update of NIST's Cybersecurity Framework. Since its launch in 2014, the Framework has become one of the most influential references for cybersecurity best practices and planning. In January, the world got ...
1 year ago Blog.isc2.org
NIST CSF Adoption and Automation - As a gold standard for cybersecurity in the United States and the foundation for many new standards and regulations starting to emerge today, the National Institute of Standards and Technology's Cybersecurity Framework is more crucial than ever. ...
10 months ago Securityboulevard.com
New NCCoE Guide Helps Major Industries Observe Incoming Data While Using Latest Internet Security Protocol - PRESS RELEASE. Companies in major industries such as finance and health care must follow best practices for monitoring incoming data for cyberattacks. The latest internet security protocol, known as TLS 1.3, provides state-of-the-art protection, but ...
9 months ago Darkreading.com
Week in review: Attackers trying to access Check Point VPNs, NIST CSF 2.0 security metrics evolution - RansomLord: Open-source anti-ransomware exploit toolRansomLord is an open-source tool that automates the creation of PE files, which are used to exploit ransomware pre-encryption. Attackers are probing Check Point Remote Access VPN devicesAttackers ...
5 months ago Helpnetsecurity.com
FAQ: What Is DFARS Compliance and How Does It Work? - Our intention is to offer a comprehensive perspective on DFARS in the context of cybersecurity, its various clauses, and the intricacies of maintaining compliance as these rules constantly shift and change over time. Size doesn't matter - big global ...
10 months ago Securityboulevard.com

Latest Cyber News


Cyber Trends (last 7 days)


Trending Cyber News (last 7 days)