Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations
Paper
โข
2303.09289
โข
Published
โข
1
OSCAR
non-profit
AI & ML interests
Large corpora
Recent Activity
View all activity
oscar-corpus's activity
mbrackย
authored
11
papers
15 days ago
Distilling Adversarial Prompts from Safety Benchmarks: Report for the Adversarial Nibbler Challenge
Paper
โข
2309.11575
โข
Published
MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation
Paper
โข
2305.15296
โข
Published
Mitigating Inappropriateness in Image Generation: Can there be Value in Reflecting the World's Ugliness?
Paper
โข
2305.18398
โข
Published
โข
1
Does CLIP Know My Face?
Paper
โข
2209.07341
โข
Published
โข
1
Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis
Paper
โข
2209.08891
โข
Published
โข
1
The Stable Artist: Steering Semantics in Diffusion Latent Space
Paper
โข
2212.06013
โข
Published
LLavaGuard: VLM-based Safeguards for Vision Dataset Curation and Safety Assessment
Paper
โข
2406.05113
โข
Published
โข
2
AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
Paper
โข
2301.08110
โข
Published
โข
1
SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs
Paper
โข
2411.07122
โข
Published
Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models
Paper
โข
2505.22232
โข
Published
โข
18
albertvillanovaย
posted
an
update
17 days ago
Post
504
New in smolagents v1.17.0:
- Structured generation in CodeAgent ๐งฑ
- Streamable HTTP MCP support ๐
- Agent.run() returns rich RunResult ๐ฆ
Smarter agents, smoother workflows.
Try it now: https://github.com/huggingface/smolagents/releases/tag/v1.17.0
- Structured generation in CodeAgent ๐งฑ
- Streamable HTTP MCP support ๐
- Agent.run() returns rich RunResult ๐ฆ
Smarter agents, smoother workflows.
Try it now: https://github.com/huggingface/smolagents/releases/tag/v1.17.0
albertvillanovaย
posted
an
update
28 days ago
Post
2442
New in smolagents v1.16.0:
๐ Bing support in WebSearchTool
๐ Custom functions & executor_kwargs in LocalPythonExecutor
๐ง Streaming GradioUI fixes
๐ Local web agents via api_base & api_key
๐ Better docs
๐ https://github.com/huggingface/smolagents/releases/tag/v1.16.0
๐ Bing support in WebSearchTool
๐ Custom functions & executor_kwargs in LocalPythonExecutor
๐ง Streaming GradioUI fixes
๐ Local web agents via api_base & api_key
๐ Better docs
๐ https://github.com/huggingface/smolagents/releases/tag/v1.16.0
alex-shvetsย
authored
a
paper
about 2 months ago
jsaizantย
authored
a
paper
about 2 months ago
albertvillanovaย
posted
an
update
about 2 months ago
Post
2757
smolagents v1.14.0 is out! ๐
๐ MCPClient: A sleek new client for connecting to remote MCP servers, making integrations more flexible and scalable.
๐ชจ Amazon Bedrock: Native support for Bedrock-hosted models.
SmolAgents is now more powerful, flexible, and enterprise-ready. ๐ผ
Full release ๐ https://github.com/huggingface/smolagents/releases/tag/v1.14.0
#smolagents #LLM #AgenticAI
๐ MCPClient: A sleek new client for connecting to remote MCP servers, making integrations more flexible and scalable.
๐ชจ Amazon Bedrock: Native support for Bedrock-hosted models.
SmolAgents is now more powerful, flexible, and enterprise-ready. ๐ผ
Full release ๐ https://github.com/huggingface/smolagents/releases/tag/v1.14.0
#smolagents #LLM #AgenticAI
sagotย
authored
a
paper
3 months ago
pjoxย
updated
a
Space
3 months ago
albertvillanovaย
posted
an
update
3 months ago
Post
4114
๐ New smolagents update: Safer Local Python Execution! ๐ฆพ๐
With the latest release, we've added security checks to the local Python interpreter: every evaluation is now analyzed for dangerous builtins, modules, and functions. ๐
Here's why this matters & what you need to know! ๐งต๐
1๏ธโฃ Why is local execution risky? โ ๏ธ
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.
2๏ธโฃ New Safety Layer in smolagents ๐ก๏ธ
We now inspect every return value during execution:
โ Allowed: Safe built-in types (e.g., numbers, strings, lists)
โ Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)
3๏ธโฃ Immediate Benefits ๐ก
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities
4๏ธโฃ Security Disclaimer โ ๏ธ
๐จ Despite these improvements, local Python execution is NEVER 100% safe. ๐จ
If you need true isolation, use a remote sandboxed executor like Docker or E2B.
5๏ธโฃ The Best Practice: Use Sandboxed Execution ๐
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.
6๏ธโฃ Upgrade Now & Stay Safe! ๐
Check out the latest smolagents release and start building safer AI agents today.
๐ https://github.com/huggingface/smolagents
What security measures do you take when running AI-generated code? Letโs discuss! ๐
#AI #smolagents #Python #Security
With the latest release, we've added security checks to the local Python interpreter: every evaluation is now analyzed for dangerous builtins, modules, and functions. ๐
Here's why this matters & what you need to know! ๐งต๐
1๏ธโฃ Why is local execution risky? โ ๏ธ
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.
2๏ธโฃ New Safety Layer in smolagents ๐ก๏ธ
We now inspect every return value during execution:
โ Allowed: Safe built-in types (e.g., numbers, strings, lists)
โ Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)
3๏ธโฃ Immediate Benefits ๐ก
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities
4๏ธโฃ Security Disclaimer โ ๏ธ
๐จ Despite these improvements, local Python execution is NEVER 100% safe. ๐จ
If you need true isolation, use a remote sandboxed executor like Docker or E2B.
5๏ธโฃ The Best Practice: Use Sandboxed Execution ๐
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.
6๏ธโฃ Upgrade Now & Stay Safe! ๐
Check out the latest smolagents release and start building safer AI agents today.
๐ https://github.com/huggingface/smolagents
What security measures do you take when running AI-generated code? Letโs discuss! ๐
#AI #smolagents #Python #Security
- 2 replies
albertvillanovaย
posted
an
update
3 months ago
Post
4018
๐ Big news for AI agents! With the latest release of smolagents, you can now securely execute Python code in sandboxed Docker or E2B environments. ๐ฆพ๐
Here's why this is a game-changer for agent-based systems: ๐งต๐
1๏ธโฃ Security First ๐
Running AI agents in unrestricted Python environments is risky! With sandboxing, your agents are isolated, preventing unintended file access, network abuse, or system modifications.
2๏ธโฃ Deterministic & Reproducible Runs ๐ฆ
By running agents in containerized environments, you ensure that every execution happens in a controlled and predictable settingโno more environment mismatches or dependency issues!
3๏ธโฃ Resource Control & Limits ๐ฆ
Docker and E2B allow you to enforce CPU, memory, and execution time limits, so rogue or inefficient agents donโt spiral out of control.
4๏ธโฃ Safer Code Execution in Production ๐ญ
Deploy AI agents confidently, knowing that any generated code runs in an ephemeral, isolated environment, protecting your host machine and infrastructure.
5๏ธโฃ Easy to Integrate ๐ ๏ธ
With smolagents, you can simply configure your agent to use Docker or E2B as its execution backendโno need for complex security setups!
6๏ธโฃ Perfect for Autonomous AI Agents ๐ค
If your AI agents generate and execute code dynamically, this is a must-have to avoid security pitfalls while enabling advanced automation.
โก Get started now: https://github.com/huggingface/smolagents
What will you build with smolagents? Let us know! ๐๐ก
Here's why this is a game-changer for agent-based systems: ๐งต๐
1๏ธโฃ Security First ๐
Running AI agents in unrestricted Python environments is risky! With sandboxing, your agents are isolated, preventing unintended file access, network abuse, or system modifications.
2๏ธโฃ Deterministic & Reproducible Runs ๐ฆ
By running agents in containerized environments, you ensure that every execution happens in a controlled and predictable settingโno more environment mismatches or dependency issues!
3๏ธโฃ Resource Control & Limits ๐ฆ
Docker and E2B allow you to enforce CPU, memory, and execution time limits, so rogue or inefficient agents donโt spiral out of control.
4๏ธโฃ Safer Code Execution in Production ๐ญ
Deploy AI agents confidently, knowing that any generated code runs in an ephemeral, isolated environment, protecting your host machine and infrastructure.
5๏ธโฃ Easy to Integrate ๐ ๏ธ
With smolagents, you can simply configure your agent to use Docker or E2B as its execution backendโno need for complex security setups!
6๏ธโฃ Perfect for Autonomous AI Agents ๐ค
If your AI agents generate and execute code dynamically, this is a must-have to avoid security pitfalls while enabling advanced automation.
โก Get started now: https://github.com/huggingface/smolagents
What will you build with smolagents? Let us know! ๐๐ก