ReskSecure가 있는 비트마스크 기반 LLM 보안 방화벽 — 토큰 레벨에서 탈옥 차단

Links:

• PyPI: https://pypi.org/project/resksecure
• GitHub: https://github.com/Resk-Security/reskSecure
• Web: https://resk.fr

Most prompt injection and jailbreak guards work by scanning output text after the model has already generated it. This is too late — the damage is done, the tool call was made, the sensitive data was exfiltrated.

reskSecure takes a different approach: block at the logits level, before the model ever samples the first forbidden token.

How it works

reskSecure uses a bitmask-based policy engine. Each policy entry defines a YAML rule with:

• A pattern to match using Aho-Corasick for multi-pattern search
• A capability bitmask that determines which tools or outputs are allowed
• A severity mode: hard (-inf logit) or bias (configurable penalty)

When a matching pattern is detected in the current token window, reskSecure either blocks the token entirely or applies a penalty to its probability. The model can never generate disallowed tool call tokens.

Quick example

# policies/block-pii.yaml
version: "1.0"
rules:
  - name: block-ssn
    patterns: ["SSN", "social security", "###-##-####"]
    severity: hard
    response: "This information cannot be shared for security reasons."

  - name: bias-unsafe-code
    patterns: ["eval(", "exec(", "__import__"]
    severity: bias
    bias_value: -5.0
    response: "This operation is restricted."

Enter fullscreen mode Exit fullscreen mode

Then use it as middleware:

from resksecure import SecurityFirewall

firewall = SecurityFirewall(
    policy_dir="./policies/",
    auto_reload=True
)

# Use as a logits processor
output = model.generate(
    input_ids=prompt,
    logits_processor=[firewall]
)

Enter fullscreen mode Exit fullscreen mode

Key features

• Token-level blocking: model never generates forbidden tokens
• Hot-reload YAML policies: change rules without restart
• Bitmask capability system: fine-grained tool access control per request
• Two severity modes: hard block or configurable bias penalty
• Aho-Corasick engine: thousands of patterns searched simultaneously
• Works with any HuggingFace model via logits processor API
• Python 3.13+, PyTorch 2.0+

Install

pip install resksecure

Enter fullscreen mode Exit fullscreen mode

Security architecture insight

Most LLM security products scan the output text after generation. reskSecure operates at the logits tensor level — it modifies the output probability distribution before token sampling. This means:

• No latency penalty from post-generation scanning
• The model can never accidentally generate the first token of a forbidden sequence
• Tool calls are blocked atomically at generation time

The bitmask approach extends naturally to multi-tenant deployments: each request gets its own capability mask, and the same firewall process enforces different policies per user context.

Conclusion

If you are deploying LLMs into production, a post-generation filter is not enough. Block at the token level with a hot-reloadable bitmask firewall.

Check the docs on resk.fr and star the repo on GitHub. Feedback and PRs welcome.

pip install resksecure
GitHub: https://github.com/Resk-Security/reskSecure
Web: https://resk.fr