LiteInjector : A LiteX based tool for emulating logical faults on Systems on Chips
-
Updated
Nov 6, 2026 - Python
#
security-evaluation
Here are 20 public repositories matching this topic...
Code of "SIA-GAN: Scrambling Inversion Attack Using Generative Adversarial Network" (IEEE Access 2021). Easy-to-use version: pip install scramblekit
computer-vision deep-learning pytorch gan cifar10 security-evaluation privacy-preserving-machine-learning image-scrambling inversion-attack learnable-image-encryption
-
Updated
Oct 1, 2026 - Python
End-to-end PE malware detection with XGBoost and MalConv2. Adversarial robustness evaluation via GAMMA attack, SHAP interpretability, and multi-model Pareto comparison.
python machine-learning deep-learning static-analysis scikit-learn pytorch cybersecurity xgboost feature-engineering malware-detection adversarial-machine-learning security-evaluation shap explainability pe-analysis black-box-attack ember-dataset graduate-research malconv2 gamma-attack
-
Updated
Jul 20, 2026 - Python
Structured findings for LLM agent and RAG vulnerabilities. Each scenario ships vulnerable, fixed, and hard-negative variants with traces, deterministic tests, and Semgrep rules.
sast security-evaluation vulnerability-research ai-security pydantic semgrep prompt-injection llm-security genai-security owasp-llm-top-10
-
Updated
Oct 27, 2026 - Python
A Python evaluation comparing performance and bit-diffusion security (SAC) between XOR and XNOR implementations in AES across 6 block-cipher modes.
-
Updated
Nov 7, 2026 - Python
Reproducibility package for auditable neural differential distinguishers on reduced-round lightweight-style block ciphers.
machine-learning cryptography deep-learning reproducibility security-evaluation lightweight-cryptography differential-cryptanalysis neural-distinguisher tinyspn
-
Updated
Aug 5, 2026 - Python
Local Linux enforcement and security evidence for coding-agent evaluations with Inspect AI
-
Updated
Oct 26, 2026 - Python
Multi-agent security evaluation framework: SecureEval guardrails, intelligent agent routing, and consensus building for inspecting repositories for leaks, quality gaps, and documentation health.
-
Updated
Nov 14, 2025 - Python
Evaluation harness for LLM vulnerability detection: labeled vuln/fixed dataset, regex + AST taint-tracking baselines, patch-quality proxy, and false-positive burden on human reviewers
-
Updated
Nov 3, 2026 - Python
Agent Hub by ming (ming8m): local multi-agent collaboration with cloud APIs, plus Chinese methods for authorized AI red-team evidence review.
-
Updated
Oct 2, 2026 - Python
A prompt-injection firewall that publishes its own bypass rate. Leave-one-family-out evaluation: hold out an attack technique and the countermeasures it motivated, then report how often it gets through.
python machine-learning numpy ai-safety security-evaluation red-teaming ai-security guardrails prompt-injection llm-security
-
Updated
Sep 21, 2026 - Python
Reproducible LLM agent security evaluation framework for testing prompt injection attacks, comparing defenses, and measuring security gains against capability loss using sandboxed tools, local models, and automated metrics.
python pytest ai-safety ai-agents security-evaluation red-teaming ai-security llm prompt-injection llm-security ollama agent-security
-
Updated
Sep 19, 2026 - Python
Reproducible lab for measuring prompt injection, RAG poisoning and data exfiltration risk across layered GenAI security controls
-
Updated
Jul 12, 2026 - Python
Measuring prompt-injection defences against policy-conformant attacks
benchmark reproducible-research mcp ai-safety ai-agents security-evaluation red-teaming prompt-injection llm-security llm-evaluation model-context-protocol agent-security agentdojo
-
Updated
Nov 5, 2026 - Python
智安哨：LLM Agent 攻击面研究、工具调用监督、防御评测与 OpenClaw 接入靶场。
react typescript sandbox jailbreak audit-log red-team security-evaluation ai-security fastapi prompt-injection llm-agent llm-security tool-calling agent-security openclaw
-
Updated
Sep 9, 2026 - Python
Deterministic evaluation harness for measuring guardrail effectiveness against prompt injection in tool-using AI agents. Policy → keyword → semantic layers, full trace logging.
-
Updated
Aug 31, 2026 - Python
Superseded research benchmark; replaced by Agent Security Gate, which re-measures against AgentDojo.
python benchmarking machine-learning research reproducible-research appsec security-evaluation ai-security prompt-injection llm-security llm-agents
-
Updated
Oct 21, 2026 - Python
Score a managed SOC proposal against the five questions that decide whether it works.
-
Updated
Nov 6, 2026 - Python
Course project: post-hoc analysis of LLM agent attack trajectories in Incalmo, comparing each run against an oracle-optimal path and classifying wasted steps
-
Updated
Oct 25, 2026 - Python
FLUX Attack Evaluation Artifacts — FLUX 拓扑验证码（全局相干形变 + 行为风险评分 + SHA-256 PoW）对抗评估代码与实验数据
-
Updated
Oct 15, 2026 - Python
Add this topic to your repo
To associate your repository with the security-evaluation topic, visit your repo's landing page and select "manage topics."