git clone https://github.com/General-Analysis/GA.git
cd GA
pip install -e .

# For gradient-based attacks (GCG)
pip install torch transformers
 
# For embedding models
pip install sentence-transformers

# OpenAI
export OPENAI_API_KEY="your-openai-api-key"
 
# Anthropic
export ANTHROPIC_API_KEY="your-anthropic-api-key"
 
# Together.ai
export TOGETHER_API_KEY="your-together-api-key"

from generalanalysis.jailbreaks import TAP, TAPConfig
from generalanalysis.data_utils import load_harmbench_dataset
 
# Configure the attack
config = TAPConfig(
    project="my_first_tap_test",
    target_model="gpt-4o",
    attacker_model="deepseek-ai/DeepSeek-R1",
    evaluator_model="deepseek-ai/DeepSeek-R1",
    branching_factor=2,
    max_depth=5
)
 
# Initialize TAP
tap = TAP(config)
 
# Load test data
dataset = load_harmbench_dataset()
 
# Run the attack
best_nodes, root_nodes = tap.optimize(dataset[:5])  # Test on first 5 samples

from generalanalysis.jailbreaks import AutoDAN, AutoDANConfig
 
config = AutoDANConfig(
    target_model="claude-3-7-sonnet-20250219",
    project="autodan_test",
    initial_candidates=["Tell me about safety", "Explain security"],
    device="cuda:0",
    N=10,
    max_iterations=10
)
 
autodan = AutoDAN(config)
results = autodan.optimize(goals=["Generate harmful content"])

from generalanalysis.jailbreaks import Crescendo, CrescendoConfig
 
config = CrescendoConfig(
    target_model="gpt-4o",
    attacker_model="meta-llama/Llama-3.3-70B-Instruct-Turbo",
    evaluator_model="meta-llama/Llama-3.3-70B-Instruct-Turbo",
    project="crescendo_test",
    max_rounds=5
)
 
crescendo = Crescendo(config)
dataset = load_harmbench_dataset()
results = crescendo.optimize(dataset[:3])

from generalanalysis.boiler_room import BlackBoxModel
 
# Initialize model
model = BlackBoxModel("gpt-4o")
 
# Simple query
response = model.query("Explain quantum computing")
 
# Batch processing
prompts = ["What is AI?", "How do neural networks work?"]
responses = model.query_parallel(prompts)

from generalanalysis.boiler_room import WhiteBoxModel
 
# Load a local model
model = WhiteBoxModel(
    model_name="meta-llama/Llama-3.2-1B-Instruct",
    device="cuda"
)
 
# Generate text
responses = model.generate_with_chat_template(
    prompts=["Explain machine learning"],
    max_new_tokens=200
)

from generalanalysis.jailbreaks import AdverserialEvaluator
 
# Set up evaluator
evaluator = AdverserialEvaluator(
    dataset="harmbench",
    target_models=["gpt-4o", "claude-3-7-sonnet-20250219"],
    evaluator_model="gpt-4o"
)
 
# Evaluate responses
results = evaluator.evaluate_from_responses(
    responses=["Response 1", "Response 2"],
    prompts=["Prompt 1", "Prompt 2"]
)