Tootfinder

Detecting, intercepting, and ejecting adversaries is getting harder as cybercriminals move faster and smarter.
Check out my latest CSO piece on how CISOs need to rethink their digital playbooks in light of these trends.
Thanks to Matt Immler of Okta, Tom Etheridge of CrowdStrike and Pierre Cadieux of Cisco Talos for their insight.

CISOs must rethink defense playbooks as cybercriminals move faster, smarter
Facing faster, stealthier intruders, CISOs are under pressure to modernize their cybersecurity strategies, toolsets, and tactics. From detection to post-mortem, here are key points of renewed emphasis.

This https://arxiv.org/abs/2505.19184 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

When Two LLMs Debate, Both Think They'll Win
Can LLMs accurately adjust their confidence when facing opposition? Building on previous studies measuring calibration on static fact-based question-answering tasks, we evaluate Large Language Models (LLMs) in a dynamic, adversarial debate setting, uniquely combining two realistic factors: (a) a multi-turn format requiring models to update beliefs as new information emerges, and (b) a zero-sum structure to control for task-related uncertainty, since mutual high-confidence claims imply systemati…

Supporting Live Music: The Importance of Shared Experiences
https://pianodao.com/2025/06/29/why-live-performance-matters/?utm_source=flipboard&utm_content=muz4now/magazine/Piano …

Supporting Live Music: The Importance of Shared Experiences
Explore the challenges facing live music and discover the importance of fostering a supportive community for performers and audiences alike.

This https://arxiv.org/abs/2505.05849 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

AGENTFUZZER: Generic Black-Box Fuzzing for Indirect Prompt Injection against LLM Agents
The strong planning and reasoning capabilities of Large Language Models (LLMs) have fostered the development of agent-based systems capable of leveraging external tools and interacting with increasingly complex environments. However, these powerful features also introduce a critical security risk: indirect prompt injection, a sophisticated attack vector that compromises the core of these agents, the LLM, by manipulating contextual information rather than direct user prompts. In this work, we pr…

Designing Algorithmic Delegates: The Role of Indistinguishability in Human-AI Handoff
Sophie Greenwood, Karen Levy, Solon Barocas, Hoda Heidari, Jon Kleinberg
https://arxiv.org/abs/2506.03102

Designing Algorithmic Delegates: The Role of Indistinguishability in Human-AI Handoff
As AI technologies improve, people are increasingly willing to delegate tasks to AI agents. In many cases, the human decision-maker chooses whether to delegate to an AI agent based on properties of the specific instance of the decision-making problem they are facing. Since humans typically lack full awareness of all the factors relevant to this choice for a given decision-making instance, they perform a kind of categorization by treating indistinguishable instances -- those that have the same o…