DITTO: A Context-aware Pickle-based Pre-Trained Model Scanner for Effective Security Audits

Reported by arXiv cs.CR (Qiaolin Qin, Wanpeng Li, Benoit Baudry, Lorenzo De Carli, Heng Li, Ettore Merlo)

Summary by Cyber Security News9 Oct 2026, 06:00 CET

About this summary. This is a short excerpt from the description that arXiv cs.CR published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2610.10735

arXiv:2610.10735v1 Announce Type: new Abstract: Pre-trained models (PTMs) are widely distributed as serialized binaries, but their reuse often exposes software supply chains to deserialization attacks. Despite the emergence of safer serialization formats, the unsafe Pickle format remains prevalent: our analysis of over 10,000 popular Hugging Face repositories reveals that 9.3% rely on Pickle.

Read the full article at arXiv cs.CR →

Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.

Related coverage

NIKKE PC launcher compromise put players’ passwords and personal files at risk

Hacking on Autopilot: Inside ARTEX Cybercrime Campaigns

Agents of chaos: the rise of the agentic swarm

Russian APT29 Targets Mobile Users with Watering Hole Attacks

ARTEX AI Pentest Tool: What Security Teams Need to Know

U.S. CISA adds Apple flaw to its Known Exploited Vulnerabilities catalog