jailbreaks
togg53192-cmd/jailbreaksCurated collection of LLM jailbreak prompts and bypass techniques, documenting adversarial inputs that circumvent AI model safety guardrails.
adversarial-attackai-securitycurated-resources+1
togg53192-cmd/jailbreaksCurated collection of LLM jailbreak prompts and bypass techniques, documenting adversarial inputs that circumvent AI model safety guardrails.
joshuagodwin7929/purple-team-automationAutomated adversary emulation (Caldera) against an AD lab to validate Sigma detection coverage and map results to MITRE ATT&CK.
bishopfox/sliverAdversary Emulation Framework
promptfoo/promptfooTest your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and…
trinib/zorg-jailbreak-prompt-textBypass restricted and censored content on AI chat prompts 😈
cybershujin/prompt-injection-in-the-wildTracker of publicly reported prompt-injection techniques, broken down by delivery method, encoding, and propagation behavior, with confirmed models,…
asset-group/ghostspliceGhostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack
meta-llama/purplellamaSet of tools to assess and improve LLM security.
guzonghua/awesome-latency-attacksCurated index of deep learning latency, energy-latency & timing (availability) attacks and defenses — companion to the ACM Computing Surveys…
giskard-ai/giskard-oss🐢 Open-Source Evaluation & Testing library for LLM Agents
thuyimingli/backdoor-learning-resourcesCurated list of backdoor learning papers, surveys, and toolboxes, organizing poisoning-based attacks and defenses in deep learning for researchers…
dovughs/mora-hwbpHardware Breakpoint (DR0-DR7) based patch-less user-mode hooking & telemetry instrumentation engine (AMSI, WLDP & ETW PoC).
rosesecurity/anti-virus-evading-payloadsDuring the exploitation phase of a pen test or ethical hacking engagement, you will ultimately need to try to cause code to run on target system…
nextronsystems/aptsimulatorA toolset to make a system look as if it was the victim of an APT attack
thunlp/openattackAn Open-Source Package for Textual Adversarial Attack.
js-lee-ai/refusal-relocatesRefusal localizes, the damage relocates, safety layers under few-sample fine-tuning
greshake/llm-securityProof-of-concept demos and research on indirect prompt injection attacks against application-integrated LLMs, covering data exfiltration, remote…
meridianlabs-ai/inspect_petriAn alignment auditing agent capable of quickly exploring alignment hypothesis