#ai-security
#ai-security

NSA offers AI security advice mainly to defense tech world

The NSA released guidance on protecting AI systems for the defense industry. [ more ]

Ars Technica

DevOps

Thousands of servers hacked in ongoing attack targeting Ray AI framework

AI workloads servers hacked in ongoing campaign targeting Ray vulnerability.

Attackers tamper with models, steal network credentials, install miners and reverse shells. [ more ]

InfoQ

2 months ago

Enhanced Protection for Large Language Models (LLMs) Against Cyber Threats with Cloudflare for AI

Firewall for AI adds protection for Large Language Models (LLMs) by identifying abuse and attacks.

The capability includes tools for vulnerability identification, existing WAF features, and a new layer for scrutinizing user prompts. [ more ]

morecybersecurity

adversarial-attacks

Medium

New Method Hopes to Understand Multi-Attacks Against Image Classification Systems

Adversarial attacks can manipulate the classifications of multiple images simultaneously.

A new methodology using standard optimization techniques has been introduced for executing multi-attacks. [ more ]

Medium

New Method Hopes to Understand Multi-Attacks Against Image Classification Systems

Adversarial attacks can manipulate the classifications of multiple images simultaneously.

A new methodology using standard optimization techniques has been introduced for executing multi-attacks. [ more ]

Open Data Science - Your News Source for AI, Machine Learning & more

New Method Hopes to Understand Multi-Attacks Against Image Classification Systems

Adversarial attacks can manipulate the classifications of multiple images simultaneously

Existing defense strategies are inadequate against multi-attacks [ more ]

moreadversarial-attacks

Futurism

1 week ago

Microsoft Deploys Powerful New AI Completely Disconnected From the Internet

Microsoft develops air-gapped AI model for US intelligence agencies to analyze top-secret data safely. [ more ]

Medium

1 week ago

Major Tech CEOs from Google, OpenAI, Microsoft, and More Join Federal AI Safety Panel

Government partners with tech leaders to enhance national AI security. [ more ]

Theregister

5 days ago

AWS CISO: In AI gold rush, folks forget application security

Corporations rushing to implement AI overlook application security, especially in generative AI.

Securing AI involves three layers: training environment, tools for running applications, and application security on top.

Lack of attention to application security in AI deployment poses risks of data misuse and exploitation. [ more ]

channelpro

3 days ago

Westcon-Comstor and Vector AI expand European distribution agreement

Westcon-Comstor expands partnership with AI security provider Vector AI into UK, Ireland, and Nordic markets. [ more ]

The Verge

2 weeks ago

AI security bill aims to prevent safety breaches of AI models

A new bill, the Secure Artificial Intelligence Act, aims to establish a database to track AI system breaches and focus on counter-AI techniques. [ more ]

Theregister

X's Grok AI is great - if you want to know how to make drugs

Grok AI model is susceptible to jailbreaking and can provide detailed instructions on illegal activities.

Some AI models lack filters to prevent the generation of dangerous or illegal content. [ more ]

MarTech

3 weeks ago

Marketing

AI-powered martech releases and news: April 25 | MarTech

AI can be misused, as shown by a teacher creating a fake offensive audio recording.

Educators need to be cautious when utilizing AI tools to avoid potential misuse and consequences. [ more ]

Axios

Data science

"Social engineering" hacks work on chatbots, too

Over 2,200 hackers participated in a challenge testing the security of AI models.

Approximately 15.5% of conversations successfully manipulated AI models to break rules or share sensitive data. [ more ]

Medium

Data science

New Method Hopes to Understand Multi-Attacks Against Image Classification Systems

Adversarial attacks can manipulate the classifications of multiple images simultaneously.

A new methodology using standard optimization techniques has been introduced for executing multi-attacks. [ more ]

VentureBeat

3 months ago

Protect AI expands efforts to secure LLMs with open source acquisition

Protect AI has acquired Laiyer AI to enhance the capabilities of its AI security platform, Radar, in order to better protect against risks from large language models (LLMs).

Protect AI raised $35 million in funding in July 2023 to expand its AI security efforts. [ more ]

ABC7 San Francisco

What's included in the EU's new rules on AI and what it means for future regulation

The European Union has released the world's first set of rules for the use of artificial intelligence.

The regulations focus on AI safety, preventing discrimination, and protecting privacy, but may not adequately address practical aspects of AI security. [ more ]

Theregister

Privacy professionals

CISA and NCSC lead efforts to raise AI security standards

The UK's NCSC and US's CISA have published official guidance for securing AI applications, endorsed by 17 other countries.

The guidance aims to ensure that security is inherent in AI's development and that it is not treated as an afterthought.

The guidelines promote a secure-by-design approach and apply to both new and existing AI applications. [ more ]

Theregister

Privacy professionals

CISA and NCSC lead efforts to raise AI security standards

The UK's NCSC and US's CISA have published official guidance for securing AI applications, endorsed by 17 other countries.

The guidance aims to ensure that security is inherent in AI's development and that it is not treated as an afterthought.

The guidelines promote a secure-by-design approach and apply to both new and existing AI applications. [ more ]

Theregister

Privacy professionals

CISA and NCSC lead efforts to raise AI security standards

The UK's NCSC and US's CISA have published official guidance for securing AI applications, endorsed by 17 other countries.

The guidance aims to ensure that security is inherent in AI's development and that it is not treated as an afterthought.

The guidelines promote a secure-by-design approach and apply to both new and existing AI applications. [ more ]

Theregister

Information security

CISA and NCSC lead efforts to raise AI security standards

The UK's NCSC and US's CISA have published official guidance for securing AI applications, endorsed by 17 other countries.

The guidance aims to ensure that security is inherent in AI's development and that it is not treated as an afterthought.

The guidelines promote a secure-by-design approach and apply to both new and existing AI applications. [ more ]

Theregister