#foilingai — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #foilingai, aggregated by home.social.
-
Information Fusion: Privacy-aware detection of fake identity documents: methodology, benchmark, and improved algorithms (FakeIDet2) . “Researchers are now trying to develop methods to detect an ever-growing number of these AI-based fakes that are almost indistinguishable from authentic (bona fide) IDs. In this counterattack effort, researchers are faced with an important challenge: the […]
https://rbfirehose.com/2026/03/30/privacy-aware-detection-of-fake-identity-documents-methodology-benchmark-and-improved-algorithms-fakeidet2-information-fusion/ -
Information Fusion: Privacy-aware detection of fake identity documents: methodology, benchmark, and improved algorithms (FakeIDet2) . “Researchers are now trying to develop methods to detect an ever-growing number of these AI-based fakes that are almost indistinguishable from authentic (bona fide) IDs. In this counterattack effort, researchers are faced with an important challenge: the […]
https://rbfirehose.com/2026/03/30/privacy-aware-detection-of-fake-identity-documents-methodology-benchmark-and-improved-algorithms-fakeidet2-information-fusion/ -
Information Fusion: Privacy-aware detection of fake identity documents: methodology, benchmark, and improved algorithms (FakeIDet2) . “Researchers are now trying to develop methods to detect an ever-growing number of these AI-based fakes that are almost indistinguishable from authentic (bona fide) IDs. In this counterattack effort, researchers are faced with an important challenge: the […]
https://rbfirehose.com/2026/03/30/privacy-aware-detection-of-fake-identity-documents-methodology-benchmark-and-improved-algorithms-fakeidet2-information-fusion/ -
Information Fusion: Privacy-aware detection of fake identity documents: methodology, benchmark, and improved algorithms (FakeIDet2) . “Researchers are now trying to develop methods to detect an ever-growing number of these AI-based fakes that are almost indistinguishable from authentic (bona fide) IDs. In this counterattack effort, researchers are faced with an important challenge: the […]
https://rbfirehose.com/2026/03/30/privacy-aware-detection-of-fake-identity-documents-methodology-benchmark-and-improved-algorithms-fakeidet2-information-fusion/ -
Information Fusion: Privacy-aware detection of fake identity documents: methodology, benchmark, and improved algorithms (FakeIDet2) . “Researchers are now trying to develop methods to detect an ever-growing number of these AI-based fakes that are almost indistinguishable from authentic (bona fide) IDs. In this counterattack effort, researchers are faced with an important challenge: the […]
https://rbfirehose.com/2026/03/30/privacy-aware-detection-of-fake-identity-documents-methodology-benchmark-and-improved-algorithms-fakeidet2-information-fusion/ -
Northeastern University: They wanted to put autonomous AI to the test. Instead, they created agents of chaos. “Dubbed ‘Agents of Chaos,’ the group’s recently published work shows how, with very little effort, autonomous AI agents can be manipulated into leaking private information, sharing documents and even erasing entire email servers.”
https://rbfirehose.com/2026/03/14/northeastern-university-they-wanted-to-put-autonomous-ai-to-the-test-instead-they-created-agents-of-chaos/ -
Northeastern University: They wanted to put autonomous AI to the test. Instead, they created agents of chaos. “Dubbed ‘Agents of Chaos,’ the group’s recently published work shows how, with very little effort, autonomous AI agents can be manipulated into leaking private information, sharing documents and even erasing entire email servers.”
https://rbfirehose.com/2026/03/14/northeastern-university-they-wanted-to-put-autonomous-ai-to-the-test-instead-they-created-agents-of-chaos/ -
Northeastern University: They wanted to put autonomous AI to the test. Instead, they created agents of chaos. “Dubbed ‘Agents of Chaos,’ the group’s recently published work shows how, with very little effort, autonomous AI agents can be manipulated into leaking private information, sharing documents and even erasing entire email servers.”
https://rbfirehose.com/2026/03/14/northeastern-university-they-wanted-to-put-autonomous-ai-to-the-test-instead-they-created-agents-of-chaos/ -
Northeastern University: They wanted to put autonomous AI to the test. Instead, they created agents of chaos. “Dubbed ‘Agents of Chaos,’ the group’s recently published work shows how, with very little effort, autonomous AI agents can be manipulated into leaking private information, sharing documents and even erasing entire email servers.”
https://rbfirehose.com/2026/03/14/northeastern-university-they-wanted-to-put-autonomous-ai-to-the-test-instead-they-created-agents-of-chaos/ -
Northeastern University: They wanted to put autonomous AI to the test. Instead, they created agents of chaos. “Dubbed ‘Agents of Chaos,’ the group’s recently published work shows how, with very little effort, autonomous AI agents can be manipulated into leaking private information, sharing documents and even erasing entire email servers.”
https://rbfirehose.com/2026/03/14/northeastern-university-they-wanted-to-put-autonomous-ai-to-the-test-instead-they-created-agents-of-chaos/ -
Digital Trends: This invisible technique poisons songs so AI can’t clone them. “The system targets a song’s waveform. My Music My Choice adds microscopic alterations so subtle that you’ll never notice them. Play the track on Spotify and it sounds exactly like the master recording. But feed that file into cloning software and everything breaks.”
https://rbfirehose.com/2026/03/06/digital-trends-this-invisible-technique-poisons-songs-so-ai-cant-clone-them/ -
Digital Trends: This invisible technique poisons songs so AI can’t clone them. “The system targets a song’s waveform. My Music My Choice adds microscopic alterations so subtle that you’ll never notice them. Play the track on Spotify and it sounds exactly like the master recording. But feed that file into cloning software and everything breaks.”
https://rbfirehose.com/2026/03/06/digital-trends-this-invisible-technique-poisons-songs-so-ai-cant-clone-them/ -
Digital Trends: This invisible technique poisons songs so AI can’t clone them. “The system targets a song’s waveform. My Music My Choice adds microscopic alterations so subtle that you’ll never notice them. Play the track on Spotify and it sounds exactly like the master recording. But feed that file into cloning software and everything breaks.”
https://rbfirehose.com/2026/03/06/digital-trends-this-invisible-technique-poisons-songs-so-ai-cant-clone-them/ -
Digital Trends: This invisible technique poisons songs so AI can’t clone them. “The system targets a song’s waveform. My Music My Choice adds microscopic alterations so subtle that you’ll never notice them. Play the track on Spotify and it sounds exactly like the master recording. But feed that file into cloning software and everything breaks.”
https://rbfirehose.com/2026/03/06/digital-trends-this-invisible-technique-poisons-songs-so-ai-cant-clone-them/ -
Lifehacker: Three Ways to Remove AI From Google. “The feature is merely summarizing answers it finds in its own web searches, which might include high-quality and accurate sources, but also low-quality, intentionally misleading, or comedic sources as well. Seeing as AI models can also make things up entirely, I personally prefer to skip the AI Overviews and evaluate individual sources on my […]
https://rbfirehose.com/2025/07/18/lifehacker-three-ways-to-remove-ai-from-google/
-
Lifehacker: Three Ways to Remove AI From Google. “The feature is merely summarizing answers it finds in its own web searches, which might include high-quality and accurate sources, but also low-quality, intentionally misleading, or comedic sources as well. Seeing as AI models can also make things up entirely, I personally prefer to skip the AI Overviews and evaluate individual sources on my […]
https://rbfirehose.com/2025/07/18/lifehacker-three-ways-to-remove-ai-from-google/
-
Lifehacker: Three Ways to Remove AI From Google. “The feature is merely summarizing answers it finds in its own web searches, which might include high-quality and accurate sources, but also low-quality, intentionally misleading, or comedic sources as well. Seeing as AI models can also make things up entirely, I personally prefer to skip the AI Overviews and evaluate individual sources on my […]
https://rbfirehose.com/2025/07/18/lifehacker-three-ways-to-remove-ai-from-google/
-
Lifehacker: Three Ways to Remove AI From Google. “The feature is merely summarizing answers it finds in its own web searches, which might include high-quality and accurate sources, but also low-quality, intentionally misleading, or comedic sources as well. Seeing as AI models can also make things up entirely, I personally prefer to skip the AI Overviews and evaluate individual sources on my […]
https://rbfirehose.com/2025/07/18/lifehacker-three-ways-to-remove-ai-from-google/
-
North Carolina State University: New Attack Can Make AI ‘See’ Whatever You Want. “Researchers have demonstrated a new way of attacking artificial intelligence computer vision systems, allowing them to control what the AI ‘sees.’ The research shows that the new technique, called RisingAttacK, is effective at manipulating all of the most widely used AI computer vision systems.”
-
North Carolina State University: New Attack Can Make AI ‘See’ Whatever You Want. “Researchers have demonstrated a new way of attacking artificial intelligence computer vision systems, allowing them to control what the AI ‘sees.’ The research shows that the new technique, called RisingAttacK, is effective at manipulating all of the most widely used AI computer vision systems.”
-
North Carolina State University: New Attack Can Make AI ‘See’ Whatever You Want. “Researchers have demonstrated a new way of attacking artificial intelligence computer vision systems, allowing them to control what the AI ‘sees.’ The research shows that the new technique, called RisingAttacK, is effective at manipulating all of the most widely used AI computer vision systems.”
-
ZDNet: Cloudflare just changed the internet, and it’s bad news for the AI giants. “The major internet Content Delivery Network (CDN), Cloudflare, has declared war on AI companies. Starting July 1, Cloudflare now blocks by default AI web crawlers accessing content from your websites without permission or compensation.”
-
ZDNet: Cloudflare just changed the internet, and it’s bad news for the AI giants. “The major internet Content Delivery Network (CDN), Cloudflare, has declared war on AI companies. Starting July 1, Cloudflare now blocks by default AI web crawlers accessing content from your websites without permission or compensation.”
-
TechXplore: Semantic watermarks for AI image recognition can be easily manipulated. ” In a talk at the Conference on Computer Vision and Pattern Recognition (CVPR 2025) on June 15 in Nashville, Tennessee, U.S., the team revealed fundamental security flaws in the supposedly resilient watermarking techniques.”
-
TechXplore: Semantic watermarks for AI image recognition can be easily manipulated. ” In a talk at the Conference on Computer Vision and Pattern Recognition (CVPR 2025) on June 15 in Nashville, Tennessee, U.S., the team revealed fundamental security flaws in the supposedly resilient watermarking techniques.”
-
Business Insider: 3 teachers tell us the changes they’re making in the classroom to address students’ rampant use of AI. “Since the release of ChatGPT in 2022 and the mass adoption of it and other generative AI tools, concerns surrounding academic plagiarism have multiplied. Educators found themselves needing to react quickly, adapting their curriculums to embrace or counter a technology that […]
-
Business Insider: 3 teachers tell us the changes they’re making in the classroom to address students’ rampant use of AI. “Since the release of ChatGPT in 2022 and the mass adoption of it and other generative AI tools, concerns surrounding academic plagiarism have multiplied. Educators found themselves needing to react quickly, adapting their curriculums to embrace or counter a technology that […]
-
Tom’s Hardware: AI agents can be manipulated into giving away your crypto, according to Princeton researchers. “Researchers from Princeton University warn of AI agents with “underexplored security risks” in a recently published paper. Dubbed ‘Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents,’ the paper (h/t Ars Technica) highlights that using AI agents […]
-
Tom’s Hardware: AI agents can be manipulated into giving away your crypto, according to Princeton researchers. “Researchers from Princeton University warn of AI agents with “underexplored security risks” in a recently published paper. Dubbed ‘Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents,’ the paper (h/t Ars Technica) highlights that using AI agents […]
-
Tom’s Hardware: AI agents can be manipulated into giving away your crypto, according to Princeton researchers. “Researchers from Princeton University warn of AI agents with “underexplored security risks” in a recently published paper. Dubbed ‘Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents,’ the paper (h/t Ars Technica) highlights that using AI agents […]
-
Tom’s Hardware: AI agents can be manipulated into giving away your crypto, according to Princeton researchers. “Researchers from Princeton University warn of AI agents with “underexplored security risks” in a recently published paper. Dubbed ‘Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents,’ the paper (h/t Ars Technica) highlights that using AI agents […]
-
Tom’s Hardware: AI agents can be manipulated into giving away your crypto, according to Princeton researchers. “Researchers from Princeton University warn of AI agents with “underexplored security risks” in a recently published paper. Dubbed ‘Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents,’ the paper (h/t Ars Technica) highlights that using AI agents […]
-
Ars Technica: Cloudflare turns AI against itself with endless maze of irrelevant facts. “On Wednesday, web infrastructure provider Cloudflare announced a new feature called ‘AI Labyrinth’ that aims to combat unauthorized AI data scraping by serving fake AI-generated content to bots. The tool will attempt to thwart AI companies that crawl websites without permission to collect training data […]
-
Ars Technica: Cloudflare turns AI against itself with endless maze of irrelevant facts. “On Wednesday, web infrastructure provider Cloudflare announced a new feature called ‘AI Labyrinth’ that aims to combat unauthorized AI data scraping by serving fake AI-generated content to bots. The tool will attempt to thwart AI companies that crawl websites without permission to collect training data […]
-
Ars Technica: Cloudflare turns AI against itself with endless maze of irrelevant facts. “On Wednesday, web infrastructure provider Cloudflare announced a new feature called ‘AI Labyrinth’ that aims to combat unauthorized AI data scraping by serving fake AI-generated content to bots. The tool will attempt to thwart AI companies that crawl websites without permission to collect training data […]
-
Ars Technica: Cloudflare turns AI against itself with endless maze of irrelevant facts. “On Wednesday, web infrastructure provider Cloudflare announced a new feature called ‘AI Labyrinth’ that aims to combat unauthorized AI data scraping by serving fake AI-generated content to bots. The tool will attempt to thwart AI companies that crawl websites without permission to collect training data […]
-
Carnegie Mellon University: CMU and MIT Join Forces To Combat Deepfake Threats. “Researchers at the Carnegie Mellon University Robotics Institute and the Massachusetts Institute of Technology, created CHARCHA ( Computer Human Assessment for Recreating Characters with Human Actions), a secure and personalized verification protocol that allows an individual’s likeness to appear in […]
-
Carnegie Mellon University: CMU and MIT Join Forces To Combat Deepfake Threats. “Researchers at the Carnegie Mellon University Robotics Institute and the Massachusetts Institute of Technology, created CHARCHA ( Computer Human Assessment for Recreating Characters with Human Actions), a secure and personalized verification protocol that allows an individual’s likeness to appear in […]
-
Carnegie Mellon University: CMU and MIT Join Forces To Combat Deepfake Threats. “Researchers at the Carnegie Mellon University Robotics Institute and the Massachusetts Institute of Technology, created CHARCHA ( Computer Human Assessment for Recreating Characters with Human Actions), a secure and personalized verification protocol that allows an individual’s likeness to appear in […]
-
Carnegie Mellon University: CMU and MIT Join Forces To Combat Deepfake Threats. “Researchers at the Carnegie Mellon University Robotics Institute and the Massachusetts Institute of Technology, created CHARCHA ( Computer Human Assessment for Recreating Characters with Human Actions), a secure and personalized verification protocol that allows an individual’s likeness to appear in […]
-
The Register: Cheap ‘n’ simple sign trickery will bamboozle self-driving cars, fresh research claims. “Eggheads have taken a look at previously developed techniques that can be used to trick self-driving cars into doing the wrong thing – and found cheap stickers stuck on stop and speed limit signs, at least, are pretty effective.”
-
The Register: Cheap ‘n’ simple sign trickery will bamboozle self-driving cars, fresh research claims. “Eggheads have taken a look at previously developed techniques that can be used to trick self-driving cars into doing the wrong thing – and found cheap stickers stuck on stop and speed limit signs, at least, are pretty effective.”
-
The Register: Cheap ‘n’ simple sign trickery will bamboozle self-driving cars, fresh research claims. “Eggheads have taken a look at previously developed techniques that can be used to trick self-driving cars into doing the wrong thing – and found cheap stickers stuck on stop and speed limit signs, at least, are pretty effective.”
-
The Register: Cheap ‘n’ simple sign trickery will bamboozle self-driving cars, fresh research claims. “Eggheads have taken a look at previously developed techniques that can be used to trick self-driving cars into doing the wrong thing – and found cheap stickers stuck on stop and speed limit signs, at least, are pretty effective.”
-
ZDNet: Anthropic offers $20,000 to whoever can jailbreak its new AI safety system. “Can you jailbreak Anthropic’s latest AI safety measure? Researchers want you to try — and are offering up to $20,000 if you succeed. On Monday, the company released a new paper outlining an AI safety system called Constitutional Classifiers. The process is based on Constitutional AI, a system Anthropic used […]
-
ZDNet: Anthropic offers $20,000 to whoever can jailbreak its new AI safety system. “Can you jailbreak Anthropic’s latest AI safety measure? Researchers want you to try — and are offering up to $20,000 if you succeed. On Monday, the company released a new paper outlining an AI safety system called Constitutional Classifiers. The process is based on Constitutional AI, a system Anthropic used […]
-
Ars Technica: New hack uses prompt injection to corrupt Gemini’s long-term memory. “In the nascent field of AI hacking, indirect prompt injection has become a basic building block for inducing chatbots to exfiltrate sensitive data or perform other malicious actions. Developers of platforms such as Google’s Gemini and OpenAI’s ChatGPT are generally good at plugging these security holes, but […]
-
Ars Technica: New hack uses prompt injection to corrupt Gemini’s long-term memory. “In the nascent field of AI hacking, indirect prompt injection has become a basic building block for inducing chatbots to exfiltrate sensitive data or perform other malicious actions. Developers of platforms such as Google’s Gemini and OpenAI’s ChatGPT are generally good at plugging these security holes, but […]
-
Ars Technica: New hack uses prompt injection to corrupt Gemini’s long-term memory. “In the nascent field of AI hacking, indirect prompt injection has become a basic building block for inducing chatbots to exfiltrate sensitive data or perform other malicious actions. Developers of platforms such as Google’s Gemini and OpenAI’s ChatGPT are generally good at plugging these security holes, but […]
-
Ars Technica: New hack uses prompt injection to corrupt Gemini’s long-term memory. “In the nascent field of AI hacking, indirect prompt injection has become a basic building block for inducing chatbots to exfiltrate sensitive data or perform other malicious actions. Developers of platforms such as Google’s Gemini and OpenAI’s ChatGPT are generally good at plugging these security holes, but […]