Papers for

chatbot and conversational ai developers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Sustained identity participation as a measurable security cost resource

Sustained Participation as a Security Resource: The Bounded Participation Channel

Abstract: Can sustained, per-identity participation be engineered into a security resource? Most anti-Sybil defenses price identity creation rather than identity survival. Once admitted, an adversary may sustain many identities without paying a recurring cost. We introduce the Bounded Participation Channel (BPC), a formal primitive for repeatedly verifying participation window by window. BPC issues fresh, identity-bound challenges under a strict deadline and enforces four structural properties: identity binding, freshness, real-time response, and bounded per-channel throughput. Together, these yield a provable cost theorem: sustaining $s$ identities over $T$ windows requires $C(s,T) \geq sT/τ_h$ participation channel-windows. The guarantee is solver-agnostic: a channel may be operated by a human, an AI system, or a hybrid. We give a hash-based construction with publicly verifiable participation proofs, characterize four admissible challenge families, and evaluate two against GPT-4o, Gemini 2.5 Flash, and Claude Sonnet 4.5 across 600 trials. Despite near-perfect accuracy (97--100%) on the perceptual tasks, the evaluated automated channels remain throughput-bounded under the tested deployment conditions. The results illustrate a key distinction: solvability does not imply unlimited throughput. By requiring participation to be re-earned by every identity in every time window, BPC turns sustained participation into a measurable security resource with a linear structural cost floor, independent of whether the participation is supplied by humans, AI systems, or hybrids.

Mon 28 SeptCryptography and Security
The gist
Many security systems try to stop attackers from creating fake identities cheaply, but once these identities get in, attackers can keep them alive without much extra effort. The authors propose a way to require ongoing proof of participation for each identity at regular times, making it costly to maintain many fake identities over time. They created a system called the Bounded Participation Channel that challenges identities repeatedly and enforces limits on how many challenges can be solved per time window. This makes it possible to track and limit sustained attack capacity whether the challenges are solved by humans, AI, or both.
Open → 2609.35300v1