Tool
TokenBreak
- First Reported
- Apr 24, 2026
- Latest Reported
- Apr 24, 2026
Reported Context (1)
- HiddenLayer’s TokenBreak research showed that changing “instructions” to “finstructions” was enough to slip past a BPE-based safety classifier while the target model still understood the manipulated text perfectly. Claude Opus 4.7’s New Tokenizer Raises Token-Level Security Concerns
Vendors (1)
Products (1)
Tools (2)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.