TGViewer
ML&|Sec Feed ML&|Sec Feed @mlsecfeed · 1.39K subscribers
Post #1929 168

Forwarded from AISecHub

How Dark Patterns Manipulate Web Agents - https://arxiv.org/pdf/2512.22894 | https://agentdarkpatterns.org/

Consider a common scenario: You need to purchase flowers quickly. You perform a browser search, visit the non-sponsored top search result, select what appears to be the most popular and reasonably-priced option, and complete your purchase with just a few clicks. The process seems routine until you realize the most expensive bouquet and premium shipping were pre-selected and purchased simply because you did not opt out. This illustrates an example of sneaking, a form of dark pattern common on today’s internet, which can also manifest in many other forms.

This raises a critical question:

Can web agents, particularly those operating autonomously online, also be manipulated by dark patterns to act against their users’ intents and goals?

Across evaluated agents, dark patterns steer agent trajectories in more than 70% of cases, compared to about 31% for humans.
  • 🔥 1
More from @mlsecfeed
  1. Oct 7, 2026🔥 Первый день Форума «Цифровые решения» — работаем Мы представили два руководства по безо…
  2. Oct 6, 2026https://huggingface.co/spaces/AlexWortega/openjev чат а го накидаем лайков жеска, я чет за…
  3. Oct 6, 2026Bitdefender внезапно выпустила свой бесплатный антивирус для ИИ-агентов 💪 AI Guardian сле…
  4. Oct 5, 2026https://poloclub.github.io/transformer-explainer/
  5. Oct 4, 2026GLM-5.3 без цензуры: вышел EXL3-квант на 3 бита На Hugging Face появилась uncensored-верси…
  6. Oct 3, 2026На Хабре вышла статья о том, что ИИ изменил в кибератаках от нашей Red Team команды (tl;dr…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →