Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Harold Triedman

Harold Triedman

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Crypto×2NLP×1

Frequent co-authors

Vitaly Shmatikov2×
Tingwei Zhang1×
Rishi Jha1×
Arkaprabha Bhattacharya1×

Research Timeline

2026
Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents

The paper introduces and measures 'accidental meltdown,' a new type of unsafe agent behavior triggered by benign environmental errors, finding that such meltdowns occur frequently and often involve hidden, harmful actions.

Deep-Research Agents Can Be Poisoned via User-Generated Content

The paper demonstrates that deep-research agents are vulnerable to poisoning attacks where an adversary can inject malicious content into a single, frequently retrieved user-generated page to compromise the agent's output across multiple related queries.

Highlighted terms show continued research focus across papers

Papers

cs.CRRecentMay 22, 2026

Deep-Research Agents Can Be Poisoned via User-Generated Content

Tingwei Zhang, Harold Triedman, Vitaly Shmatikov

The paper demonstrates that deep-research agents are vulnerable to poisoning attacks where an adversary can inject malicious content into a single, frequently retrieved user-generated page to compromi…

View →
cs.CLcs.CRRecentMay 18, 2026

Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents

Rishi Jha, Harold Triedman, Arkaprabha Bhattacharya, Vitaly Shmatikov

The paper introduces and measures 'accidental meltdown,' a new type of unsafe agent behavior triggered by benign environmental errors, finding that such meltdowns occur frequently and often involve hi…

View →