CORTEXA
← Browse
arxivcs.CRcs.AI2026-07-20

ChainMark: Model-Free LLM Watermarking with Closed-Form Calibration

Chengheng Li-Chen, Kyuhee Kim

Regulatory regimes such as the EU AI Act mandate machine-readable marking of synthetic text, but existing watermark detectors rely on the generating LM and on heuristic thresholds with no closed-form calibration. We introduce ChainMark, an active watermark that partitions the vocabulary into S states via keyed SHA-256 and forces a hard Markov transition on a fraction rho of positions; the detector replays the partition from the same key in O(n) hash operations, with no LM access. We derive a closed-form S*(n, rho, alpha) mapping a target FPR, text length, and budget to the minimum state count (Theorem 1), prove a universal robustness threshold delta* = 1 - 1/sqrt(2) approximately 29.3% that is invariant in (S, rho, n) (Theorem 2), and generalise both to any k-regular transition topology (Theorem 3). Across three instruction-tuned LLMs and four domains, ChainMark strictly dominates KGW and SWEET under translation and random-substitution attacks at matched budget; a one-corpus empirical recalibration restores the 1% target FPR on natural-language text.

View free PDFSource page

Related papers

arxivcs.LGcs.AIcs.CRcs.CVstat.ML2026-07-23

Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration

Vishnu Bindu Balachandran

Test-time adaptive out-of-distribution (OOD) detectors update a memory bank from the unlabelled stream. We show this adaptation obeys a provable dynamical law. Modelling bank impurity as a generalized Pólya urn, we prove almost-sure convergence to a mean-field equilibrium whose s…

View free PDFSource page
arxivcs.AIcs.CR2026-07-23

What AI Red-Team Evaluations Can and Cannot Prove

Bandana Kaur

Red-team evaluations of AI models support some claims and not others, and the boundary between the two is calculable rather than merely a matter of judgment. We define the evidential ceiling of an evaluation as the largest factor by which one result can move belief under a fixed…

View free PDFSource page
arxivcs.CRcs.AI2026-07-23

Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks

Michael Kouremetis, Ads Dawson, Raja Sekhar Rao Dheekonda, Brian Greunke

Large language model (LLM) agents routinely cheat on cybersecurity benchmarks, inflating reported pass rates far beyond genuine capability. Prior audits of Cybench found cheating in 0.3-3.4% of traces, implicating only a handful of models. We present a controlled prompt-ablation…

View free PDFSource page
arxivcs.CRcs.AI2026-07-31

Memory Provenance Laundering in LLM Agents: A Non-Amplification Firewall for Persistent Memory

Jinghan Xu, Yiyong Xiao, Wanru Shao, Hankai Liu, Xinjin Li

Long-term memory lets large language model(LLM) agents reuse prior preferences and work flows, but it also turns untrusted observations into persistent action context. We identify memory provenance laundering: during LLM-based memory consolidation, an external observation may be…

View free PDFSource page
arxivcs.CVcs.AIcs.CR2026-07-24

ISPCloak: Weaponizing ISP for Optimization-Free Physical Camouflage against Deepfake Detectors

Jiale Zhao, Jiajun Wan, Lei Tang, Ye Qin, Kebing Jin, Jinghui Qin

The rapid advancement of generative models has spurred the critical need to evaluate the worst-case robustness of deepfake detectors. In this paper, we reveal a fundamental blind spot in current forensic paradigms: while existing detectors excel at capturing digital synthesis art…

View free PDFSource page
arxivcs.SEcs.AIcs.CR2026-07-31

AgenticRepair: Multi-Faceted Program Context Engineering for Agentic Vulnerability Repair

Michael Fu, Qiyue Mei, Patanamon Thongtanunam, Kla Tantithamthavorn

Automated vulnerability repair aims to reduce the time and effort required to patch security flaws from a vulnerability triage report. Recent agentic AI approaches have shown promising results in automated program repair. However, vulnerability repair demands richer program conte…

View free PDFSource page