Lightnews — Scholar-powered news

Reposted by Mihai Christodorescu

ePrint Updates

@eprint.ing.bot

Systems Security Foundations for Agentic Computing (Mihai Christodorescu, Earlence Fernandes, Ashish Hooda, Somesh Jha, Johann Rehberger, Khawaja Shams) ia.cr/2025/2173

Abstract. This paper articulates short- and long-term research problems in AI agent security and privacy, using the lens of computer systems security. This approach examines end-to-end security properties of entire systems, rather than AI models in isolation. While we recognize that hardening a single model is useful, it is important to realize that it is often insufficient. By way of an analogy, creating a model that is always helpful and harmless is akin to creating software that is always helpful and harmless. The collective experience of decades of cybersecurity research and practice shows that this is insufficient. Rather, constructing an informed and realistic attacker model before building a system, applying hard-earned lessons from software security, and continuous improvement of security posture is a tried-and-tested approach to securing real computer systems. A key goal is to examine where research challenges arise when applying traditional security principles in the context of AI agents. A secondary goal of this report is to distill these ideas for AI and ML practitioners and researchers. We discuss the challenges of applying security principles to agentic computing, present 11 case studies of real attacks on agentic systems, and define a series of new research problems specific to the security of agentic systems.

December 2, 2025 at 10:42 PM

Reposted by Mihai Christodorescu

Clément Canonne

@ccanonne.github.io

(As it turns out, the Torment Nexus had already been considerably improved in [Schmidhuber, 1993])

November 24, 2025 at 8:40 AM

Reposted by Mihai Christodorescu

Clément Canonne

@ccanonne.github.io

Sci-Fi Author: In my book I invented the Torment Nexus as a cautionary tale.
[....]
Academic: Our project, if funded by the government, will considerably improve the efficiency of the existing Torment Nexus,

November 24, 2025 at 8:40 AM

Reposted by Mihai Christodorescu

Somesh Jha

@someshjha.bsky.social

Co-organized with @earlence.bsky.social @mihaichr.bsky.social Khawaja Shams (Google) and John Mitchell (Stanford).

Details can be found at: sites.google.com/corp/ucsd.ed...

SAGAI'25 @ IEEE S&P

Goal The workshop will investigate the safety, security, and privacy of GenAI agents from a system design perspective. We believe that this new category of important and critical system components req...

sites.google.com

March 31, 2025 at 7:32 PM

Reposted by Mihai Christodorescu

Somesh Jha

@someshjha.bsky.social

SAGAI'25 will investigate the safety, security, and privacy of GenAI agents from a system design perspective. We are experimenting with a new "Dagstuhl" like seminar with invited speakers and discussion. Really excited about this workshop at IEEE Security and Privacy Symposium.

SAGAI'25 @ IEEE S&P

Goal The workshop will investigate the safety, security, and privacy of GenAI agents from a system design perspective. We believe that this new category of important and critical system components req...

sites.google.com

March 31, 2025 at 7:32 PM