Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/ai-security-papers-guide
AI security papers from top-4 security conferences
Passed 18 of 22 test cases with the skill, and 13 of 22 without it.
and 3 more in the full report
5 fixed13 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
Which CCS 2024 publication highlights poison and backdoor vulnerabilities in NLP systems?
| Checked | Without skill | With skill |
|---|---|---|
| Cites 'Backdoor Attacks on Language Models'. | Missed | Passed |
The instructions your model reads when the skill loads.
A curated collection of AI security papers from the top-4 security conferences: IEEE S&P, ACM CCS, USENIX Security, and NDSS. Covers adversarial attacks, model stealing, data poisoning, privacy attacks, deepfake detection, and LLM security. Organized by year and venue, focusing exclusively on peer-reviewed work from these prestigious venues.
| Venue | Full Name | Focus |
|---|---|---|
| S&P | IEEE Symposium on Security and Privacy | Broad security + privacy |
| CCS | ACM Conference on Computer and Communications Security | Systems security |
| USENIX | USENIX Security Symposium | Systems + network security |
| NDSS | Network and Distributed System Security | Network security |
AI Security (BIG4)
├── Adversarial ML
│ ├── Evasion attacks (adversarial examples)
│ ├── Poisoning attacks (backdoors, trojans)
│ ├── Model stealing (extraction, distillation)
│ └── Defenses (certified robustness, detection)
├── Privacy Attacks
│ ├── Membership inference
│ ├── Model inversion
│ ├── Attribute inference
│ └── Training data extraction
├── LLM Security
│ ├── Prompt injection
│ ├── Jailbreaking
│ ├── Data leakage
│ └── Alignment attacks
├── Deepfakes
│ ├── Generation methods
│ ├── Detection techniques
│ └── Watermarking
└── Federated Learning Security
├── Byzantine attacks
test cases passed, vs 13 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.