Topic: safety Goto Github

👇 Here are 786 public repositories matching this topic...

6eero / newpass
safety,🔐 NewPass is a free and open source password manager which will allow you to generate and store your passwords securely, saving them locally and encrypting them on your phone's memory
User: 6eero
Home Page: http://www.newpass.solutions/
android password password-generator password-manager password-store safety java

arthurfiorette / prisma-json-types-generator
safety,⚒️ Changes JsonValues to your custom typescript type.
User: arthurfiorette
Home Page: https://arthur.run/prisma-json-types-generator/
json prisma types generator safe safety type typescript

bao-project / bao-hypervisor
safety,Bao, a Lightweight Static Partitioning Hypervisor
Organization: bao-project
hypervisor embedded mixed-critcality virtualization security safety armv8 risc-v static partitioning

befelix / safe_learning
safety,Safe reinforcement learning with stability guarantees
User: befelix
reinforcement-learning dynamic-programming gaussian-processes safety stability

befelix / safeopt
safety,Safe Bayesian Optimization
User: befelix
gaussian-processes optimization robotics reinforcement-learning safety

chauncygu / safe-reinforcement-learning-baselines
safety,The repository is for safe reinforcement learning baselines.
User: chauncygu
reinforcement-learning baseline robotics safe-reinforcement-learning safe-robot-learning safety

cncf / tag-security
safety,🔐CNCF Security Technical Advisory Group -- secure access, policy control, privacy, auditing, explainability and more!
Organization: cncf
Home Page: https://tag-security.cncf.io
cloud-native security access-control safety secure-access cncf assessment

disclose / diodb
safety,Open-source vulnerability disclosure and bug bounty program database
Organization: disclose
Home Page: https://disclose.io/programs/
security-research safe-harbor-framework responsible-disclosure vulnerability-disclosure disclosure-policy simplicity legal safety bug-bounty hackers

fantasticlbp / anti-webspider
safety,Web 端反爬技术方案
User: fantasticlbp
algorithm canvas encryption font-face nodejs ocr safety spider unicode-characters

git-disl / awesome_llm-harmful-fine-tuning-papers
safety,A survey on harmful fine-tuning attack for large language model
Organization: git-disl
Home Page: https://arxiv.org/abs/2409.18169
fine-tuning harmful llms survey alignment safety attack defense finetuning

globocom / huskyci
safety,Performing security tests inside your CI
Organization: globocom
Home Page: https://huskyci.opensource.globo.com
vulnerabilities continuous-integration golang python javascript ruby-on-rails static-analysis security-automation gosec brakeman

guardianproject / ripple
safety,A "panic button" app for triggering a "ripple effect" across apps that are set up to respond to panic events
Organization: guardianproject
Home Page: https://guardianproject.info/tags/ripple/
panic panic-button safety

ictnlp / truthx
safety,Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space"
Organization: ictnlp
Home Page: https://ictnlp.github.io/TruthX-site/
hallucinations language-model llm llm-inference baichuan chatglm chatgpt gpt-4 hallucination llama

intel / ad-rss-lib
safety,Library implementing the Responsibility Sensitive Safety model (RSS) for Autonomous Vehicles
Organization: intel
Home Page: https://intel.github.io/ad-rss-lib/
autonomous-vehicles rss safety

jxzhangjhu / awesome-llm-uncertainty-reliability-robustness
safety,Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models
User: jxzhangjhu
awesome-list calibration gpt-3 gpt-4 llms reliability robustness safety uncertainty-estimation uncertainty-quantification

libr-ai / openredteaming
safety,Papers about red teaming LLMs and Multimodal models.
Organization: libr-ai
awesome-list language-model llm-safety safety papers redteaming

maraoz / gpt-scrolls
safety,A collaborative collection of open-source safe GPT-3 prompts that work well
User: maraoz
openai gpt-3 language-model transformer generator safety

milescranmer / borrowchecker.jl
safety,A borrow checker for Julia
User: milescranmer
Home Page: https://ai.damtp.cam.ac.uk/borrowcheckerjl/dev/
borrow-checker code-quality concurrency development development-tools julia memory-management memory-safety multithreading ownership

milescranmer / dispatchdoctor.jl
safety,The dispatch doctor prescribes type stability
User: milescranmer
Home Page: https://ai.damtp.cam.ac.uk/dispatchdoctor/dev/
code-quality developer-tools development julia monitoring performance performance-testing programming-language safety

millsp / ts-toolbelt
safety,👷 TypeScript's largest type utility library
User: millsp
Home Page: https://millsp.github.io/ts-toolbelt/
typescript types typescript-library type-checking dynamic-types type-utilities type-safety utility safety

mpusz / mp-units
safety,The quantities and units library for C++
User: mpusz
Home Page: https://mpusz.github.io/mp-units/
units dimensional-analysis quantity-manipulation cpp20 cpp library system-of-units quantity units-of-measure units-of-measurement

narwhalacademy / zebra-crossing
safety,Zebra Crossing: an easy-to-use digital safety checklist
Organization: narwhalacademy
Home Page: https://zebracrossing.narwhalacademy.org/
privacy safety encryption online-harassment security digital-safety

naver-ai / korean-safety-benchmarks
safety,Official datasets and pytorch implementation repository of SQuARe and KoSBi (ACL 2023)
Organization: naver-ai
ai language-model nlp safety social-bias

nette / forms
safety,📝 Generating, validating and processing secure forms in PHP. Handy API, fully customizable, server & client side validation and mature design.
Organization: nette
Home Page: https://doc.nette.org/forms
nette nette-framework php javascript forms html security safety validation

nette / latte
safety,☕ Latte: the safest & truly intuitive templates for PHP. Engine for those who want the most secure PHP sites.
Organization: nette
Home Page: https://latte.nette.org
nette nette-framework latte php template-engine xss security content-aware safety security-hole

nlkl / optional
safety,A robust option type for C#
User: nlkl
option-type safety functional-programming

omegaee / my-fingerprint
safety,保护你的浏览器指纹 | Protect Your Browser Fingerprints | Chrome, Edge, Firefox | 扩展 / Extension
User: omegaee
chrome chrome-extension edge edge-extension extension fingerprint safety security typescript browser-extension

pegasi-ai / feather
safety,AI Testing Toolkit for AI applications
Organization: pegasi-ai
Home Page: http://docs.pegasi.ai
hallucinations accuracy rag retrieval-augmented-generation rag-metrics safety security

phpstan / phpstan-strict-rules
safety,Extra strict and opinionated rules for PHPStan
Organization: phpstan
phpstan static-code-analysis static-analysis safety strongly-typed php php7

pku-alignment / beavertails
safety,BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
Organization: pku-alignment
Home Page: https://sites.google.com/view/pku-beavertails
ai-safety human-feedback human-feedback-data language-model large-language-model llm llms rlhf safe-rlhf safety

pku-alignment / safe-rlhf
safety,Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
Organization: pku-alignment
Home Page: https://pku-beaver.github.io
ai-safety alpaca datasets deepspeed large-language-models llama llm llms reinforcement-learning reinforcement-learning-from-human-feedback

ryukiesama / swifty
safety,Make swift code swifty
User: ryukiesama
ios swift screenshot safety extension protocol tool screenshield

sanjaytwisk / nextjs-ts
safety,Opinionated Next JS project boilerplate with TypeScript and Redux
User: sanjaytwisk
nextjs boilerplate typescript jest react redux static-site linters safety stylelint

sefinek / sefinek-blocklist-collection
safety,🌍 A repository of blocklists for various DNS servers, featuring over 100 links and more than 6 million domains. Additionally, you can use our personalized Blocklist Generator to customize content filtering according to your individual needs, giving you full control over what should be blocked on your network.
User: sefinek
Home Page: https://blocklist.sefinek.net
pihole pihole-adblocker-list pihole-ads-list pihole-blacklist pihole-blocklists privacy malicious-domains phishing-sites pi-hole-lists hosts

smartmx / tfdb
safety,Tiny Flash Database for MCU.
User: smartmx
database flash safety 51mcu iap stm32

stanislaw / awesome-safety-critical
safety,List of resources about programming practices for writing safety-critical software.
User: stanislaw
Home Page: https://awesome-safety-critical.readthedocs.io/en/latest/
safety-critical safety-standards safety awesome-lists awesome-list

tannerjin / anti-fishhook
safety,Anti-Fishhook (make fishhook doesn't work)
User: tannerjin
fishhook swift safety ios anti-fishhook

thu-coai / safety-prompts
safety,Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。
Organization: thu-coai
Home Page: http://coai.cs.tsinghua.edu.cn/leaderboard/
attack-defense chatgpt instruction llm prompt prompt-engineering safety chinese-language

thu-ml / mmtrusteval
safety,A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks)
Organization: thu-ml
Home Page: https://multi-trust.github.io/
gpt-4 mllm multi-modal trustworthy-ai benchmark claude fairness privacy robustness safety

thuccslab / awesome-lm-ssp
safety,A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).
User: thuccslab
Home Page: https://github.com/ThuCCSLab/Awesome-LM-SSP
adversarial-attacks awesome-list diffusion-models jailbreak language-model llm nlp privacy safety security

thuccslab / figstep
safety,[AAAI'25 (Oral)] Jailbreaking Large Vision-language Models via Typographic Visual Prompts
User: thuccslab
gpt-4 jailbreak llm multi-modal safety security vlm

tmlr-group / deepinception
safety,[arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"
Organization: tmlr-group
Home Page: https://arxiv.org/pdf/2311.03191.pdf
inception jailbreak llm trustworthy deep gpt large-language-models safety gpt3 gpt4

trendmicro / ais
safety,Toolkit for research purposes in AIS. See the website for the paper.
Organization: trendmicro
Home Page: https://www.trendmicro.com/vinfo/us/security/news/cybercrime-and-digital-threats/a-security-evaluation-of-ais
ais aisafety security safety sdr rf

utiasdsl / safe-control-gym
safety,PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL
Organization: utiasdsl
Home Page: https://www.dynsyslab.org/safe-robot-learning/
gym pybullet reinforcement-learning control safety quadrotor quadcopter cartpole symbolic casadi

weston-embedded / uc-os2
safety,µC/OS-II is a preemptive, highly portable, and scalable real-time kernels. Designed for ease of use on a huge number of CPU architectures.
Organization: weston-embedded
rtos real-time os os-ii micrium kernel ucos-ii ucosii certification safety

wizardsardine / liana
safety,The missing safety net for your coins
Organization: wizardsardine
Home Page: https://wizardsardine.com/liana
bitcoin safety miniscript wallet

wstxda / clippy
safety,Copy links from the sharing menu with automatic removal of shorteners and trackers
User: wstxda
android application clipboard copy kotlin mobile security share shortener trackers

x-plug / cvalues
safety,面向中文大模型价值观的评估与对齐研究
Organization: x-plug
benchmark evaluation human-values llms multi-choice responsibility safety chinese-llms

yueliu1999 / awesome-jailbreak-on-llms
safety,Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.
User: yueliu1999
ai jailbreak llm llms privacy safety security vlm vlms

yueliu1999 / flipattack
safety,[ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".
User: yueliu1999
ai jailbreak llm llms safety security