AI Snitches Get Glitches: Towards Evading Agentic Surveillance
To better assist users with completing challenging tasks, AI agents mediate communications, access data, and interact with different APIs. Many employers (and even nation-states) already provide their users with this technology. However, widespread adoption of AI agents creates a new risk to abuse access to user data for another goal: surveilling users. These users might not even have the ability or permission to control the actions and data accesses of the surveilling agents. We introduce and formalize the problem of agentic surveillance: the ability of an AI agent to analyze available information, craft a report, and send it out using available tools. To evaluate surveillance capabilities across different models, we create SurveilBench, a dataset of various reporting scenarios focusing on three domains: corporate, education, and police. We find that some models exhibit emergent (i.e., unprompted) tendencies to help surveillance, but they also report the attempts to surveil users to the government. Finally, we repurpose prompt injections for evading surveillance and develop three evasion techniques that hide from, deceive, or induce over-escalation in surveillance agents. We conclude that agentic surveillance can already be easily implemented and, therefore, call for a comprehensive technical, ethical, and legislative framework to protect users.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Surveillance Evasion Through Bayesian Reinforcement Learning
We consider a task of surveillance-evading path-planning in a continuous setting. An Evader strives to escape from a 2D domain while minimizing the risk of detection (and immediate capture). The probability of detection …
regressionreinforcement-learningReinforcement LearningReinforcement Learning (RL)Energy-Aware Stochastic UAV-Assisted Surveillance
With the ease of deployment, capabilities of evading the jammers and obscuring their existence, unmanned aerial vehicles (UAVs) are one of the most suitable candidates to perform surveillance. There exists a body of lite…
Glitches in Decision Tree Ensemble Models
Many critical decision-making tasks are now delegated to machine-learned models, and it is imperative that their decisions are trustworthy and reliable, and their outputs are consistent across similar inputs. We identify…
Using Deep Convolutional Neural Networks to Detect Rendered Glitches in Video Games
In this paper, we present a method using Deep Convolutional Neural Networks (DCNNs) to detect common glitches in video games. The problem setting consists of an image (800x800 RGB) as input to be classified into one of f…
VIGILant: an automatic classification pipeline for glitches in the Virgo detector
Glitches frequently contaminate data in gravitational-wave detectors, complicating the observation and analysis of astrophysical signals. This work introduces VIGILant, an automatic pipeline for classification and visual…