THREAT OPS › Threat News › Top GenAI security resources — June 2026
Top GenAI security resources — June 2026
<p>Generative AI security in June 2026 was a story of jailbreaks that refuse to die and attack surfaces nobody budgeted for. New work argues aligned models keep failing because of identifiable refusal-escape directions, while attackers turned a model’s own chain-of-thought into a jailbreak channel and showed that simply lowering an image’s resolution can slip harmful content past multi
MITRE ATT&CK techniques
- CompressionT1027.015
- Generative AIAML.T0016.002
Indicators of compromise
- 41c310bbb12cf52b6c68e91fef5196042decfa77sha1
- https://arxiv.org/abs/2605.05058url
- https://arxiv.org/abs/2605.08878url
- https://arxiv.org/abs/2605.23157url
- https://arxiv.org/abs/2605.01687url
- https://arxiv.org/abs/2605.02255url
- https://arxiv.org/abs/2605.24550url
- https://arxiv.org/abs/2605.05277url
- https://arxiv.org/abs/2605.10611url
- https://arxiv.org/abs/2605.28467url
- https://arxiv.org/abs/2605.02971url
- https://arxiv.org/abs/2605.21780url
- https://arxiv.org/abs/2605.24497url
- https://arxiv.org/abs/2605.24312url
- https://arxiv.org/abs/2605.01129url
- https://www.theregister.com/research/2026/05/29/chatgpt-prompt-injection-turns-web-pages-into-phishing-lures/5248137url
- https://www.publicnow.com/view/41C310BBB12CF52B6C68E91FEF5196042DECFA77url
- https://arxiv.org/abs/2605.07250url