AI Security Trend Roundup — May 29, 2026
Covering May 22 → May 29, 2026. 55 new items from 8 tracked sources.
This digest credits every source by name and links directly to each original post. Editorial curation by FixTheVuln — all rights and attribution belong to the original authors.
Academic & Research
Source: arXiv cs.CR — May 29 arXiv:2605.28899v1 Announce Type: new Abstract: Artificial Intelligence has achieved remarkable success across diverse application domains. However, its vulnerability to adversarial attacks poses significant challenges to reliability, security, and trustworthiness. Adversarial ma
Source: arXiv cs.CR — May 29 arXiv:2605.28914v1 Announce Type: new Abstract: Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model Context Protocol tools. This makes agent attacks different from jailbreaks. The har
Source: arXiv cs.CR — May 29 arXiv:2605.28999v1 Announce Type: new Abstract: LLMs are vulnerable to prompt injection attacks. However, this vulnerability has been primarily demonstrated conceptually in academic studies or through a few anecdotal case studies. Its prevalence and impact in real-world LLM-based
Source: arXiv cs.CR — May 29 arXiv:2605.29107v1 Announce Type: new Abstract: Large language models (LLMs) increasingly rank products, documents, and recommendations for user queries, which makes manipulating these rankings a growing concern for fairness and information integrity. Research on generative engin
Source: arXiv cs.CR — May 29 arXiv:2605.29178v1 Announce Type: new Abstract: As agentic coding systems decompose work across multiple model instances, a critical safety question is whether those instances can coordinate to achieve a hidden malicious objective while remaining aligned with user intent. We intr
Source: arXiv cs.CR — May 29 arXiv:2605.29210v1 Announce Type: new Abstract: The growing integration of artificial intelligence (AI) and machine learning (ML) in medical systems requires effective measures to address emerging security risks. One such risk is that of adversaries introducing false data through
Source: arXiv cs.CR — May 29 arXiv:2605.29237v1 Announce Type: new Abstract: Jailbreak attacks on large language models (LLMs) aim to induce LLMs to produce content that they are expected to refuse. Automated black-box jailbreak generation is especially important for safety evaluation, where the attacker obs
Source: arXiv cs.CR — May 29 arXiv:2605.29245v1 Announce Type: new Abstract: This paper presents a survey and taxonomy of LLM fingerprinting and watermarking for identity, ownership verification, provenance, and generated-content attribution. Large language models (LLMs) require substantial investments in da
Source: arXiv cs.CR — May 29 arXiv:2605.29269v1 Announce Type: new Abstract: Modern alert-triage systems reduce SOC burden by filtering false positives, but flagging a high-risk alert is only the start of incident response. Threat hunting requires reconstructing causal attack chains across heterogeneous, par
Source: arXiv cs.CR — May 29 arXiv:2605.29353v1 Announce Type: new Abstract: The proliferation of AI-generated synthetic media poses a critical threat to the integrity of digital evidence in legal and forensic contexts. Existing deepfake detection systems typically address a single modality and provide no me
Source: arXiv cs.CR — May 29 arXiv:2605.29354v1 Announce Type: new Abstract: LLM-powered coding agents increasingly participate in software development workflows by generating code, selecting dependencies, and producing package installation commands. This creates a new software supply chain risk: when an age
Source: arXiv cs.CR — May 29 arXiv:2605.29434v1 Announce Type: new Abstract: Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence split
Source: arXiv cs.CR — May 29 arXiv:2605.29450v1 Announce Type: new Abstract: The need for secure and private Artificial Intelligence (AI) and Machine Learning (ML) on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy.
Source: arXiv cs.CR — May 29 arXiv:2605.29468v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to support scientific work, but it is unclear whether they uphold responsible conduct of research (RCR) norms or help undermine them. We introduce SciIntBench, an adversarial benchm
Prompt Injection & LLM Security
Source: Simon Willison — May 29 Release: datasette 1.0a31 Another significant alpha release, with two new headline features. Datasette now offers users with the necessary permissions the ability to both execute write queries against their database and to save stored queries (renamed from "canned queries") both
Source: Simon Willison — May 29 The most interesting thing about Anthropic's $65B Series H announcement is this line (emphasis mine): Since our Series G in February, adoption has continued to grow across global enterprise customers, and our run-rate revenue crossed $47 billion earlier this month. Anthropic have
Source: Simon Willison — May 28 Anthropic shipped Claude Opus 4.8 today. My favourite thing about it is this note in the release announcement: Users will find Opus 4.8 to be a modest but tangible improvement on its predecessor. There’s still more to be done: we’re working on developing and releasing models that
Source: Simon Willison — May 28 Release: llm-anthropic 0.25.1 New model: Claude Opus 4.8 (claude-opus-4.8). New -o fast 1 option for fast mode, for organizations with that feature enabled on their account. Default max_tokens for each model now defaults to that model's maximum output rather than 8,192. #72 See a
Source: Simon Willison — May 28 Tool: markdown-svg-renderer A slightly customized Markdown rendering tool with special treatment for fenced code SVG blocks - it both renders the image and provides a tab for switching to the code view. You can paste in Markdown or give it a URL to a CORS-enabled Markdown file or
Source: Simon Willison — May 27 sqlite AGENTS.md SQLite gained an AGENTS.md file five days ago - but it's not intended for their own development, it's presumably aimed at people who are pointing agents at the SQLite codebase. It includes: SQLite does not accept pull requests without prior agreement and/or accom
Source: Simon Willison — May 27 Anthropic are strongly rumored to be about to have their first profitable quarter. Stories are circulating of companies surprised at how expensive their LLM bills are becoming from usage by their staff. I think this is because OpenAI and Anthropic have both found product-market f
Source: Simon Willison — May 27 PICARD: Data, shields up DATA: Brilliant! Shields can reduce damage we sustain. Not immunity. Not hubris. Just prudence. It's not precaution—it's strategy. [camera shakes] WORF: HULL BREACHES ON NINE DECKS DATA: Here's what happened: you told me to raise shields, and I didn't &md
Source: Simon Willison — May 26 The pressure Daniel Stenberg on the unprecedented level of pressure the curl team are facing right now thanks to the deluge of (credible) AI-assisted security issues being reported. The rate of incoming security reports is 4-5 times higher than it was in 2024 and double the speed
Source: Simon Willison — May 26 Microsoft Copilot Cowork Exfiltrates Files The biggest challenge in designing agentic systems continues to be preventing them from enabling attackers to exfiltrate data. In this case Microsoft Copilot Cowork (yes, that's a real product name) was allowing agents to send emails to
Source: Simon Willison — May 26 A lot of the emails I get from founders are now written in a hard-hitting journalistic style. I know they're written by AI, because no founder ever wrote this way before. And once you realize something is written by AI, it's hard not to ignore it. I have never knowingly finished
Source: Simon Willison — May 26 I cannot believe I'm saying this, but getting the literal Pope to canonize your product's specific technical limitations as a spiritual treatise is the single greatest act of vendor lobbying I have ever seen. — Corey Quinn, on Anthropic co-founder Christopher Olah's influen
Source: Simon Willison — May 25 Dropped this morning by the Vatican: Magnifica Humanitas of His Holiness Pope Leo XIV on Safeguarding the Human Person in the Time of Artificial Intelligence. This is a very interesting document. It's some of the clearest writing I've seen on the ethics of integrating AI into mod
Source: Simon Willison — May 25 California Brown Pelican, Snowy Egret, California Sea Lion, Harbor Seal, in San Mateo County, CA, USWe took our new folding kayak out in the harbor and saw sea lions and harbor seals chilling on the docks.
Source: Simon Willison — May 24 Release: datasette 1.0a30 The big new feature in this alpha is a new customizable "Jump to..." menu, described in detail in The extensible "Jump to" menu in Datasette 1.0a30 on the Datasette blog. You can try it out by hitting / on latest.datasette.io - it looks like this: The ne
Source: Simon Willison — May 24 Release: datasette-agent 0.1a4 Taking advantage of the new makeJumpSections() JavaScript plugin hook added in Datasette 1.0a30, datasette-agent now presents this "Start a new agent chat" interface as part of the Jump to menu, any time you hit /: You can try this out by signing in
Source: Simon Willison — May 24 Release: datasette-fixtures 0.1a0 One of the smaller features in Datasette 1.0a30 is this: New documented datasette.fixtures.populate_fixture_database(conn) helper for creating the fixture database tables used by Datasette's own tests, intended for plugin test suites. This new pl
Source: Simon Willison — May 24 The most frustrating failure mode right now is that people submit issues that are not in their own voice. They contain an observed problem somewhere, but it has been thrown into a clanker and the clanker reworded it and made a huge mess of it. Typically, it was prompted so badly
Source: Simon Willison — May 24 Tool: Mad House — Usborne Creepy Computer Games Via Hacker News I learned that UK publisher Usborne published free PDFs of their 1980s Computer Books, some of which I remember working through on my Commodore 64 as a child. These were so great! Beautifully illustrated books with f
Source: Simon Willison — May 23 On the
- I learned a few new-to-me things about the
- can be followed by multiple
- You can optionally group the
- and
- elements in a for styling - but only a. You can label them using ARIA. They've been c
Source: Simon Willison — May 22 The memory shortage is causing a repricing of consumer electronics David Oks provides the clearest explanation I've seen yet of why consumer products that use memory are likely to get significantly more expensive over the next few years. The short version is that memory manufactu
Community Signal
Source: Hacker News (AI Security) — May 29 Article URL: https://koenvangilst.nl/lab/mistral-ai-now-summit Comments URL: https://news.ycombinator.com/item?id=48325340 Points: 64 # Comments: 7
Source: Hacker News (AI Security) — May 29 Article URL: https://twitter.com/suekhim/status/2060378988606878147 Comments URL: https://news.ycombinator.com/item?id=48324357 Points: 23 # Comments: 1
Source: Hacker News (AI Security) — May 29 Article URL: https://shawnsmucker.substack.com/p/please-use-ai Comments URL: https://news.ycombinator.com/item?id=48323101 Points: 646 # Comments: 318
Source: Hacker News (AI Security) — May 29 Hi, I’m Kenny, I’ve been building aislop. I starting working on this after using Claude Code, codex and opencode several times and noticing some slops. They aren’t syntax and passes most tests, they are patterns like empty catch blocks, useless comments, duplicated helpers, dead
Source: Hacker News (AI Security) — May 29 Article URL: https://www.moderndescartes.com/essays/ai_and_expertise/ Comments URL: https://news.ycombinator.com/item?id=48322929 Points: 52 # Comments: 54
Source: Hacker News (AI Security) — May 29 Article URL: https://mastrojs.github.io/blog/2026-05-23-is-AI-causing-a-repeat-of-frontends-lost-decade/ Comments URL: https://news.ycombinator.com/item?id=48321631 Points: 192 # Comments: 186
Source: Hacker News (AI Security) — May 29 Article URL: https://blog.kog.ai/real-time-llm-inference-on-standard-gpus-3-000-tokens-s-per-request/ Comments URL: https://news.ycombinator.com/item?id=48321076 Points: 162 # Comments: 73
Source: Hacker News (AI Security) — May 29 Article URL: https://arstechnica.com/security/2026/05/fed-up-with-vibe-coders-dev-sneaks-data-nuking-prompt-injection-into-their-code/ Comments URL: https://news.ycombinator.com/item?id=48319968 Points: 50 # Comments: 64
Source: Hacker News (AI Security) — May 29 Article URL: https://finance.yahoo.com/sectors/technology/articles/microsoft-data-suggests-using-ai-225900743.html Comments URL: https://news.ycombinator.com/item?id=48317563 Points: 66 # Comments: 14
Source: Hacker News (AI Security) — May 29 Article URL: https://minimaxir.com/2026/05/openrouter-hy3/ Comments URL: https://news.ycombinator.com/item?id=48317294 Points: 89 # Comments: 77
Source: Hacker News (AI Security) — May 28 Article URL: https://www.tomshardware.com/tech-industry/cyber-security/microsofts-github-bans-security-researcher-who-posted-zero-day-windows-exploits-because-company-ruined-their-life-expert-claims-action-is-vindictive-and-promises-further-retaliation Comments URL: https://news.
Source: Hacker News (AI Security) — May 28 Article URL: https://www.ft.com/content/b1a62a7f-6df5-4c90-94ce-64ce9c9961b6 Comments URL: https://news.ycombinator.com/item?id=48315583 Points: 69 # Comments: 19
Source: Hacker News (AI Security) — May 28 https://archive.ph/50zy3 Comments URL: https://news.ycombinator.com/item?id=48314363 Points: 227 # Comments: 175
Source: Hacker News (AI Security) — May 28 Article URL: https://shvbsle.in/various-llm-smells/ Comments URL: https://news.ycombinator.com/item?id=48313810 Points: 345 # Comments: 267
Source: Hacker News (AI Security) — May 28 Article URL: https://kristoff.it/blog/llms-at-zig-days/ Comments URL: https://news.ycombinator.com/item?id=48313219 Points: 82 # Comments: 69
Source: Hacker News (AI Security) — May 28 Article URL: https://futuresearch.ai/blog/agi-timeline-tracker/ Comments URL: https://news.ycombinator.com/item?id=48309344 Points: 45 # Comments: 81
Source: Hacker News (AI Security) — May 28 Article URL: https://llmgame.scalex.dev Comments URL: https://news.ycombinator.com/item?id=48308376 Points: 363 # Comments: 147
Source: Hacker News (AI Security) — May 28 Article URL: https://lenz.io/research/llm-disagreement Comments URL: https://news.ycombinator.com/item?id=48307887 Points: 498 # Comments: 342
Source: Hacker News (AI Security) — May 28 Article URL: https://twitter.com/kevinsays/status/2059724146221662339 Comments URL: https://news.ycombinator.com/item?id=48307455 Points: 26 # Comments: 17
Source: Hacker News (AI Security) — May 28 Article URL: https://www.axios.com/2026/05/28/ai-spending-roi-enterprise-costs Comments URL: https://news.ycombinator.com/item?id=48307098 Points: 165 # Comments: 143
Source List
All sources tracked in this roundup, credited to their original authors/organizations:
- OWASP GenAI Security Project — feed:
https://genai.owasp.org/feed/ - Simon Willison — feed:
https://simonwillison.net/atom/everything/ - arXiv cs.CR — feed:
http://export.arxiv.org/rss/cs.CR - Protect AI — feed:
https://protectai.com/blog/rss.xml - Google Project Zero — feed:
https://googleprojectzero.blogspot.com/feeds/posts/default - CISA Cybersecurity Advisories — feed:
https://www.cisa.gov/cybersecurity-advisories/all.xml - NIST Cybersecurity News — feed:
https://www.nist.gov/news-events/cybersecurity/rss.xml - Hacker News (AI Security) — feed:
https://hnrss.org/newest?q=%22AI+security%22+OR+%22prompt+injection%22+OR+%22LLM+vulnerability%22&points=20
Explore More
FixTheVuln Store
Studying for Security+? Get the Study Planner
Structured study planners for CompTIA certifications. Domain trackers, time blocking, and exam strategies.
Shop Security+ PlannerAlso available: CompTIA A+, Network+, CySA+, PenTest+
← Back to Home ← All Blog PostsCyberFolio
Building cybersecurity skills? Track them in one place.
Build a shareable cybersecurity portfolio that highlights your certifications, projects, and skills — free.
Build Your Portfolio → - OWASP GenAI Security Project — feed:
- element from this article by Ben Meyer: A