InfoResearchPeer-reviewedLLM-specific
Robustness Over Time: Understanding Adversarial Examples’ Effectiveness on Longitudinal Versions of Large Language Models
- Published
- Record updated
Summary
A longitudinal study tested the adversarial robustness of GPT, Llama and Qwen model families across successive versions, covering misclassification, jailbreak and hallucination. The authors found that LLM updates do not consistently improve robustness: a later GPT-3.5 version got worse on misclassification and hallucination despite better jailbreak resilience. GPT-4 and GPT-4o showed incrementally higher overall robustness, while larger Llama and Qwen models did not uniformly improve, and larger size did not reliably help.
Topics
Related items
- InfoSoftBank plunges over 16% as AI sell-off hits Asian tech stocks following Anthropic debutSame vendor · CNBC Technology
- InfoGPT-6.2 Astra vs. Sol: Features, Pricing & Security | StraikerSame vendor · Straiker Blog
- InfoMeta’s Muse Charm might cost $300Same vendor · The Verge (AI)
- InfoThreatsDay: GPT-6.2 Jailbreak Flaws, BubbleLoader PNG Malware, $500M Ransom Demands + 17 More StoriesSame vendor · The Hacker News
- InfoChatGPT can transcribe as you speak now with Live DictationSame vendor · The Verge (AI)